Raiders owner Mark Davis fired head coach Josh McDaniels and GM Dave Ziegler on Halloween night just 25 games into their tenures in Sin City.

Las Vegas Raiders fire Josh McDaniels and Dave Ziegler, promote Giant Super Bowl champ Antonio Pierce to interim HC

Seismic unrest can be a sign that a volcano is waking up, but the full story is much more complex.

Two supervolcanoes, a world apart, have the attention of scientists

Variety's interview studio during Advertising Week featured conversations with marketing leaders in the industry, in partnership with Canva.

Inside Variety’s New Leaders Studio Presented by Canva

The retail giant has recruited much of the original cast of the 2004 comedy classic Mean Girls — including stars Lindsay Lohan , Amanda Seyfried, Lacey Chabert, Daniel Franzese and Rajiv Surendra — to star in a Black Friday marketing campaign.

‘Mean Girls’ Cast Reunites for Walmart Black Friday Ad Campaign

In case you were unaware, Christian Siriano leads an incredibly busy life between working on new collections and red carpet looks, his role as a mentor for Project Runway (which he won back in 2008),

Christian Siriano Wants You to Read the Britney Spears Memoir in His New Robe

Now DeSantis is settling into his role as an all-purpose political punching bag. Presidential hopefuls Nikki Haley, Vivek Ramaswamy, Tim Scott and Christie have all taken swipes at DeSantis in the hopes of reviving their own stagnant campaigns. In debates, DeSantis now spends as much time being mocked as he does speaking.

‘Bootgate’ and pudding fingers: How Ron DeSantis became 2024’s presidential punchline

The 49ers have lost three straight games following a 15-game win streak in the regular season, including Sunday's 31-17 home loss to the Bengals. It was a prime opportunity for Brock Purdy and company to make a statement against a Super Bowl contender after an upset loss in Minnesota.

Do the 49ers have a Brock Purdy problem? Determining how much young QB is to blame for 3-game losing streak

Thomas Rhett, Lauren Akins and all four daughters journey into Super Mario World as they celebrate Halloween. The couple is parents to daughters Willa, Ada, Lennon, and Lillie.

Thomas Rhett, Lauren Akins and All Four Daughters Journey into Super Mario World for Halloween

LAS VEGAS—Of all the VIPs to grace the Republican Jewish Coalition with their attendance at the group’s annual leadership conference, Miriam Adelson may have been the most significant.

Republican Superdonor Miriam Adelson Is Back

Never Back Down, the super PAC supporting Florida Gov. Ron DeSantis’ 2024 White House bid, is hoping to reach voters who want to move on from Donald Trump in their advertising.

As Ron DeSantis drops in polls, backers zero in on tired-of-Trumpers

Get the most recent info and news about Super on HackerNoon, where 10k+ technologists publish stories for 4M+ monthly readers.

As the first social commerce platform in Indonesia that is ISO 9001:2015 certified, Aplikasi Super aims to solve economic inequality across cities for Indonesia’s future economy. Aplikasi Super is one of top YC companies, which oversees the main feature, SuperAgen, which is agent-led commerce that enables community leaders to become retailers within the communities.

Super

In this article, I'll show you how to quickly setup pretty URLs in Super with a little shell command and a Node.js script. If you are reading this, you may already be aware that helps you go public with your pages.  What you may not know, is that ugly URLs are And notion's got some ugly URLs. https://super.so https://www.notion.so bad for SEO. It should come as no surprise that the easier a URL is to read for humans, the better it is for search engines - Rand Fishkin Well, color me surprised!  I've never needed to give SEO any thought before, but now it's my job to care!  It's time to accommodate the web crawlers and get our new and pages indexed. help careers So the first step to getting all your links pretty and into Super, is to get all the links off of your notion page.  In the case of the new Hacker Noon help page (http://help.hackernoon.com/), there were links to pretty up in this super form: 157 That's a lot of copy-pasting and clicking around and coming up with pretty URLs and so I decided to open up my chrome browser's network tab and see what was being sent to the server so I could just give it a single payload with all the links in it. DISCLAIMER:  Using any site a way not intended by the developers may result loss data.  Proceed at your own risk!  (maybe start a little test where it won in in of with 't hurt anything:) To to get the network tab, one needs to open the developer console.  On a mac, this is done with cmd+option+i.  You can also reach this by clicking the ellipsis/hamburger menu (three dots, in a column) button, going to More Tools and then finally Developer Console A portion of your window should be covered with a new panel and at the top of that, you should see some tabs.  One of those is called Network and will provide us with a template to use in our own payload to send to Super. You can see Network selected here with the blue underline.  If I click on the clear button 🚫 next to the red circle, it'll clear out any previous network calls so we can clearly see what is sent when we save our pretty URLs. Here we see a bunch of requests that happened, but the POST that goes to a URL called "update" looks interesting for our use case.  (You may need to right-click the columns to select "Method" to be able to show that column)  You can also use the search box with to filter to just those types of calls, if you already know what you are looking for. method:POST If you click on the method and look at the Headers tab that will show up, then scroll to the bottom of that, you will see the request payload. Open that up and see where the stuff you typed into the pretty URL window is. In this cast, there is a field called prettyUrls that is an array of objects with two fields, which ends up just getting the ugly, unique identifier portion of a notion URL, and also a field which is where it will redirect.  So now we know what we are doing, we need an array of objects with all our notion page ids and the URLs they are going to.  Upwards and onwards! pageId url Right-click that method and select if you want to write a node.js script like I did.  Maybe you're into curl or using fetch right in the browser's console. Copy > Copy as Node.js fetch Okay, so you've got this node code in our paste buffer and nowhere to put it!  It's time to make a script and paste it in there. We are going to ignore it for now though because I wrote this article a little out of order and I can't drag things around to reorder them and I'm just gonna roll with it! Let's move on to getting all the notion links off the page.   One way this can be done is by downloading the page and its links with: wget -r -l0 https://help.hackernoon.com/ This took a few minutes and may have been overkill, but when it was done I had a neat little help.hackernoon.com folder with a bunch of HTML files.  I ended up using the HTML files to come up with the pretty URL so maybe not overkill.  Here's a bit of what it looked like in that directory when I listed the files: help.hackernoon.com ls
0109b933c3084e9699b408a73b142e8a  5c115f8cb76445788bb16a4499758cd8  d1edc21b1f2d48d9afa43f4da6d4cc4f
0142ddfc63b94ef9a1ca01975c3d2cab  5c45cf10b99046939df336a23ddae597  d44cdbf1e6d94c0eab9fb5091c249e97
028466d28622424ca1523069faf1d7c6  5f54fe2e3b6641b3b1d49f7b47a961d7  db9dd7e7998141df9705628b03fcd75b
033557c93f714ae092e13e095ca9c2cf  604adc1e960840b782d7f2de2687f719  de55338768674dccbc80909d4ccea58f Cool, so all these piles of alpha-numeric characters are the notion entry to put in the left side of that form. To get the corresponding pretty URL to put on the right-hand side, I peeked inside one of the files and looked for where the header was by searching for h1 There it is with the juicy "Hacker Noon Editor 101" meat/text inside.  Now to start a script to iterate over all these files and parse and kebab-case the h1 headers. I used , which is jQuery for node.js, to do this.  This is how things started to look: the library cheerio fs = ( ); cheerio = ( ); { files = fs.promises.readdir( ); ( file files) { stat = fs.promises.stat(file); (stat.isDirectory()) ; html = fs.readFileSync(file).toString(); $ = cheerio.load(html); contents = $( ).contents()[ ]; (!contents) ; url = contents.data; .log(url);
  }
})(); const require "fs" const require "cheerio" ( )=> ( async const await "./" for const of const await if continue //we just want the html files const const const 'h1' 0 if continue const console So this script was run from inside that help.hackernoon.com so it could find the files easily with the path. Next, we used the function to help us determine if it was a file or directory, as there was one directory to skip. ./ stat _next Maybe you think the is whack, because it is synchronous? You are correct. readFileSync It doesn't matter though, this is just a one-off script to get the job done.  We call on that to be able to pass the wad of HTML text at cheerio and now we can run selectors on it to scrape it. toString() I needed the first h1 so our selector is simply that and we to get the first one, maybe it found more, if it didn't we continue going to the next file.  After that the schema cheerio gives you dictates that to get the text out you will need to ask for the to get the text.  All these get logged out and I could see if things were looking good. [0] .data By the way, one nice way to work on things like this and get quick feedback is to use another package https://nodemon.io/ which can be installed globally to use as a shell command or as a library to be used for your own file watching needs, like if you want to roll your own hot reloading framework for node development.  In this case, my script was called sendIt.js and so I could run in one split pane of my terminal and anytime I saved the file in another split, the file was re-run and I got a handy feedback loop. nodemon sendIt.js Okay, it's time to combine the node.js fetch bit with this loop that gets all the URL mappings. I'm going to plop in a gist now that should get the idea across.  The new code added to our existing code is just adding a Set and then adding our pretty URL objects to that. You may also notice that I am adjusting the pretty URL around line 22. It's there that we modify the h1 text by making it lowercase on line and removing invalid URL characters. Spaces become dashes, double dashes turn back into one dash, strips out the non-dashes and all non-alphanumeric characters.  Next, leading and trailing dashes are removed. /[^0-9a-z-]/gi This could be condensed into less replace calls, but this is readable and this code will only ever run when you want to update your pretty URLs so I am not going to sweat it. Next, around , I skip some files with dots because those were downloaded but don't need mappings, like index.js.  You could also just delete them from the folder of links that were downloaded. line 29 with the body was created by copying the string from the node.js fetch code we pasted in from the developer console into a node REPL and running on that.  Now it's some code, so we can get a chance to take our Set of prettyUrls and get them into our payload. will turn the Set into an array. Line 42 JSON.parse Array.from(prettyUrls) The rest of the fetch is unchanged, save for the body section where I it back into the original format we pasted in.  I save this fetch call as a variable so I can print it and see what any issues are.  There are always issues with the first (through at least the 10th) attempt. JSON.stringify In my case, the lines about stripping our invalid chars, having duplicate entries that were already added to the list of pretty URLs and all that were my issues that caused me to iterate a few times on this.  So there were more console.logs sprinkled throughout this code to help me identify where things went wrong. If the result of the fetch has a and the word OK, you are good. Refresh your pretty URL list and double-check.  If you get a 500 and a Bad Gateway, you probably sent an invalid character in the URL or sent a duplicate entry. status 200 So there you have it, you can use these ideas in a lot of other places than just notion and super.  Just be careful you try out ideas on something else first that you are not worried about screwing up if you send the wrong payload.  The saying "Measure twice, cut once" comes to mind. Anywho, I hope this was helpful.  You can tell me your thoughts about it on Twitter if you really want.  I primarily wrote this to help me get over my writer's block and just publish .  ✌️ something

How to Clean Up Notion URLs: From Ugly URLs to Pretty URLs in Minutes

19 July, 2024/--SINGAPORE – ZKEX.com, the industry’s first multi-chain Super DEX, has raised $2.5 million in its latest funding round. This seed round features investors such as Fenbushi Capital, KXVC, and RockTree Capital. The funds will support ZKEX.com’s roadmap to launch its fiat on-ramp service, mobile app, and Telegram bot in the upcoming quarter. ZKEX.com offers crypto traders the functionality of a centralized exchange (CEX), including multi-chain Convert, Spot, Derivatives, and cross-chain Bridging. Unlike traditional CEXs, ZKEX.com allows users to trade native assets on any blockchain directly from their self-custodial wallets, eliminating the need to hand over token custody to the exchange. The protocol is the first decentralized exchange (DEX) in industry to address the problem of liquidity fragmentation across different blockchains by using zero-knowledge technology to create a secure, unified trading layer. The round saw participation from Fenbushi Capital, KXVC, RockTree Capital, NGC Ventures, L2 Iterative Ventures, Crypto.com Capital, IDG Blockchain, Whale Ground, Moonhill Capital, Blocklabs Capital, Optic Capital, Hyperithm Group, and G20 Group. Over the past 12 months, decentralized crypto exchanges have experienced significant growth, with monthly trading volumes rising from approximately $100 billion to over $250 billion by early 2024. This growth aligns with an increase in active user wallets from 3 million to over 4 million and zero-knowledge projects securing over $400 million in funding. “We’re obsessed with making multi-chain trading simple, fast, and cheap, offering a similar experience to a CEX without compromising the principles of self-custody and decentralization,” said Balal Khan, co-founder. “Users can onboard from any network and start trading with native assets in under a minute. In a few clicks, you could use your USDT on zkSync to spot buy ETH, short sell it with a perpetual contract, close both positions as limit orders, and withdraw profits as USDC on Base.” Security remains a critical concern in the blockchain industry, with over 150 major hacks involving cross-chain bridges and exchanges in the past two years, leading to billions in lost or stolen crypto assets. “ZKEX.com has addressed one of crypto’s biggest security challenges - the ability to safely use any supported stablecoin to directly trade tokens on any connected chain, without intermediaries,” said Omer Ozden, Chairman of RockTree Capital. “The core team brings years of experience from top-tier CEXs to decentralized on-chain trading, and we’re excited for what’s ahead,” he added. ZKEX.com operates on an aggregated Layer 3 (L3) built on zkLink, LayerZero, and Polyhedra, guaranteeing the security of deposits, withdrawals, and transactions across chains with zero-knowledge proofs and achieving settlement speeds of up to 1000 transactions per second. About ZKEX ZKEX.com is the Web3 industry’s first Super DEX, an ultra-secure, multi-chain crypto exchange that offers the functionality of a centralized exchange while maintaining asset self-custody. Users can trade tokens and move assets across 10 chains and rollups, including Ethereum, BNB Chain, Polygon, Avalanche, Arbitrum, Optimism, Base, zkSync, Linea, and opBNB. All transactions are secured with zero-knowledge proofs, ensuring the safety of users’ funds at all times. For media inquiries, please contact team@zkex.com Website: zkex.com ｜ Docs  ｜ Blog  ｜  Twitter ｜ Discord ｜ Telegram This story was distributed as a release by Btcwire under HackerNoon’s Business Blogging Program. Learn more about the program here. 19 July, 2024/--SINGAPORE – ZKEX.com, the industry’s first multi-chain Super DEX, has raised $2.5 million in its latest funding round. This seed round features investors such as Fenbushi Capital, KXVC, and RockTree Capital. The funds will support ZKEX.com’s roadmap to launch its fiat on-ramp service, mobile app, and Telegram bot in the upcoming quarter. ZKEX.com offers crypto traders the functionality of a centralized exchange (CEX), including multi-chain Convert, Spot, Derivatives, and cross-chain Bridging. Unlike traditional CEXs, ZKEX.com allows users to trade native assets on any blockchain directly from their self-custodial wallets, eliminating the need to hand over token custody to the exchange. ZKEX.com ZKEX.com The protocol is the first decentralized exchange (DEX) in industry to address the problem of liquidity fragmentation across different blockchains by using zero-knowledge technology to create a secure, unified trading layer. The round saw participation from Fenbushi Capital, KXVC, RockTree Capital, NGC Ventures, L2 Iterative Ventures, Crypto.com Capital, IDG Blockchain, Whale Ground, Moonhill Capital, Blocklabs Capital, Optic Capital, Hyperithm Group, and G20 Group. Over the past 12 months, decentralized crypto exchanges have experienced significant growth, with monthly trading volumes rising from approximately $100 billion to over $250 billion by early 2024. This growth aligns with an increase in active user wallets from 3 million to over 4 million and zero-knowledge projects securing over $400 million in funding. “We’re obsessed with making multi-chain trading simple, fast, and cheap, offering a similar experience to a CEX without compromising the principles of self-custody and decentralization,” said Balal Khan, co-founder. “Users can onboard from any network and start trading with native assets in under a minute. In a few clicks, you could use your USDT on zkSync to spot buy ETH, short sell it with a perpetual contract, close both positions as limit orders, and withdraw profits as USDC on Base.” “We’re obsessed with making multi-chain trading simple, fast, and cheap, offering a similar experience to a CEX without compromising the principles of self-custody and decentralization,” said Balal Khan, co-founder. “Users can onboard from any network and start trading with native assets in under a minute. In a few clicks, you could use your USDT on zkSync to spot buy ETH, short sell it with a perpetual contract, close both positions as limit orders, and withdraw profits as USDC on Base.” Security remains a critical concern in the blockchain industry, with over 150 major hacks involving cross-chain bridges and exchanges in the past two years, leading to billions in lost or stolen crypto assets. “ZKEX.com has addressed one of crypto’s biggest security challenges - the ability to safely use any supported stablecoin to directly trade tokens on any connected chain, without intermediaries,” said Omer Ozden, Chairman of RockTree Capital. “The core team brings years of experience from top-tier CEXs to decentralized on-chain trading, and we’re excited for what’s ahead,” he added. “ZKEX.com has addressed one of crypto’s biggest security challenges - the ability to safely use any supported stablecoin to directly trade tokens on any connected chain, without intermediaries,” said Omer Ozden, Chairman of RockTree Capital. “The core team brings years of experience from top-tier CEXs to decentralized on-chain trading, and we’re excited for what’s ahead,” he added. ZKEX.com operates on an aggregated Layer 3 (L3) built on zkLink, LayerZero, and Polyhedra, guaranteeing the security of deposits, withdrawals, and transactions across chains with zero-knowledge proofs and achieving settlement speeds of up to 1000 transactions per second. ZKEX.com ZKEX.com About ZKEX ZKEX.com is the Web3 industry’s first Super DEX, an ultra-secure, multi-chain crypto exchange that offers the functionality of a centralized exchange while maintaining asset self-custody. Users can trade tokens and move assets across 10 chains and rollups, including Ethereum, BNB Chain, Polygon, Avalanche, Arbitrum, Optimism, Base, zkSync, Linea, and opBNB. All transactions are secured with zero-knowledge proofs, ensuring the safety of users’ funds at all times. For media inquiries, please contact team@zkex.com team@zkex.com team@zkex.com Website: zkex.com ｜ Docs ｜ Blog ｜ Twitter ｜ Discord ｜ Telegram zkex.com zkex.com Docs Docs Blog Blog Twitter Twitter Discord Discord Telegram Telegram This story was distributed as a release by Btcwire under HackerNoon’s Business Blogging Program. Learn more about the program here. This story was distributed as a release by Btcwire under HackerNoon’s Business Blogging Program. Learn more about the program here . here here

ZKEX.com Unveils ‘Super DEX’ Following $2.5m Fundraise

Hey there, data aficionados! Today, we're diving into the world of real estate and private equity, where data is king (or maybe queen, depending on your market). But extracting that data? That can be a royal pain. Just ask our client, a digital middle-office solutions provider who was drowning in a sea of paperwork. Let me tell you, manually extracting data from asset valuation reports, real estate assessments, and lease collection records is enough to make anyone cry. It's slow, tedious, and prone to errors. Our client was facing a triple threat: Manual data extraction: Extracting data by hand is like washing dishes – never-ending and frankly, soul-crushing.
Document complexity: These documents weren't your friendly neighborhood grocery list. They were unstructured, long-winded beasts with tables that would make a mathematician weep.
Time consumption: Manually wrangling this data was a black hole, sucking away precious time and resources. There had to be a better way: Gen AI. The Quest for Efficiency: Why We Needed Automation Our client needed a data extraction knight in shining armor, a solution that could automate the process, improve efficiency, and free them from the shackles of manual data entry. Here's what they were looking for: Efficiency – Slashing the manual workload associated with data extraction.
Accuracy – Extracting data with laser-like precision to ensure reliable information.
Document Flexibility – Handling diverse document types, from unstructured chaos to neat and tidy tables. Building the Dream Team: Gen AI and AWS Bedrock We knew a one-size-fits-all approach wouldn't cut it. So, we assembled a dream team of technologies, with Gen AI and AWS Bedrock leading the charge. Here's how we tackled the challenge: Building a Fortress: The Power of AWS – We leveraged the mighty AWS cloud environment, utilizing AWS Bedrock services to construct a robust backend. This fortress provided a secure and scalable foundation for our custom-developed solutions.
Document Parsing with Gen AI: The Brains of the Operation – Powered by AWS Bedrock, we built a custom-made document parser. This intelligent tool was like Sherlock Holmes for documents, analyzing their structure and content to identify and extract relevant data fields with pinpoint accuracy.
Specialized Pipelines: Tailored for Every Document – We didn't believe in a "one size fits all" approach. Instead, we designed specialized data extraction pipelines for each document type, ensuring optimal performance and accuracy for every format, from asset valuation reports to real estate assessments.
Advanced AI Models and Tools: The Superpower Squad – We assembled a league of extraordinary AI models and tools to achieve the best possible results. OpenSearch provided a search platform with flexibility and scalability, while FAISS facilitated the efficient retrieval of similar documents. Additionally, we leveraged the power of foundation models like Titan and Cohere, along with Retrieval-Augmented Generation (RAG) to take the extraction process to the next level.
Integration with Scanned Documents: No Doc Left Behind – We knew scanned documents were a reality, so we integrated AWS Textract. This powerful tool extracts data from scanned documents with impressive accuracy, ensuring seamless processing of all document formats.
Data Quality: Our Top Priority – Maintaining data accuracy was paramount. We implemented rigorous Data Quality (DQ) checks across the extracted data, employing filtering mechanisms to guarantee clean and reliable outputs. This ensured the client received trustworthy data, ready for further use. By combining these elements, we created a comprehensive solution that addressed the client's specific needs for efficient and accurate data extraction from complex and varied documents. Quantifiable Success: The Numbers Don't Lie The impact of our Gen AI-powered solution was clear as day (and measurable!). Here's how Gen AI helped our client achieve significant improvements: Soaring Accuracy: 87% Across the Board – Our client craved data accuracy, and we delivered. Our solution achieved an impressive 87% accuracy rate across all document types. This meant the extracted data was reliable and ready for further analysis and use without extensive manual verification.
Dramatic Reduction in Manual Effort: From Days to Hours – The time-consuming nature of manual data extraction was a major bottleneck for the client. Our solution streamlined the process, resulting in a staggering 700x reduction in manual effort. Imagine tasks that previously took days to complete, now achievable in a matter of hours. Think of the reallocated resources and the potential for increased productivity! That's a 700x time multiplier, folks. That's like shaving weeks off a project, freeing up your team to focus on higher-level tasks, strategic analysis, or even chasing that elusive work-life balance.
Significant Cost Savings: A 4x Advantage – The efficiency gains brought about by automation also yielded substantial cost savings for the client. By eliminating the need for manual data extraction, the client achieved a 4x reduction in costs. These savings can be re-invested in further growth initiatives, expanding their service offerings, or even delighting their clients with lower fees. Beyond the Numbers: The Ripple Effect of Efficiency The benefits of our solution extended far beyond the numbers. Here's what our client experienced: Improved Decision-Making: With accurate and timely data at their fingertips, the client could confidently make data-driven decisions.
Enhanced Client Service: Faster turnaround times and improved data quality translated into better service for their clients.
Increased Scalability: The automation freed up resources, allowing the client to scale their operations and easily handle a larger volume of data. The Takeaway: Gen AI and AWS Bedrock - Your Data Extraction Dream Team This project is a testament to Gen AI's and AWS Bedrock's power. By combining these innovative technologies, we were able to transform a tedious and error-prone process into a streamlined and efficient operation. If you're drowning in a sea of documents and struggling with data extraction, don't despair! We can help you build your own dream team. Indium's expertise in Gen AI and our understanding of your industry challenges can help you unlock the potential of your data and achieve remarkable results. So, are you ready to say goodbye to manual data extraction and hello to a world of efficiency and productivity? Let's chat! We're here to help you turn your data extraction woes into a thing of the past. Hey there, data aficionados! Today, we're diving into the world of real estate and private equity, where data is king (or maybe queen, depending on your market). But extracting that data? That can be a royal pain. Just ask our client, a digital middle-office solutions provider who was drowning in a sea of paperwork. Let me tell you, manually extracting data from asset valuation reports, real estate assessments, and lease collection records is enough to make anyone cry. It's slow, tedious, and prone to errors. Our client was facing a triple threat: Manual data extraction: Extracting data by hand is like washing dishes – never-ending and frankly, soul-crushing. Document complexity: These documents weren't your friendly neighborhood grocery list. They were unstructured, long-winded beasts with tables that would make a mathematician weep. Time consumption: Manually wrangling this data was a black hole, sucking away precious time and resources. Manual data extraction: Extracting data by hand is like washing dishes – never-ending and frankly, soul-crushing. Manual data extraction: Document complexity: These documents weren't your friendly neighborhood grocery list. They were unstructured, long-winded beasts with tables that would make a mathematician weep. Document complexity: Time consumption: Manually wrangling this data was a black hole, sucking away precious time and resources. Time consumption: There had to be a better way: Gen AI. The Quest for Efficiency: Why We Needed Automation Our client needed a data extraction knight in shining armor, a solution that could automate the process, improve efficiency, and free them from the shackles of manual data entry. Here's what they were looking for: Efficiency – Slashing the manual workload associated with data extraction. Accuracy – Extracting data with laser-like precision to ensure reliable information. Document Flexibility – Handling diverse document types, from unstructured chaos to neat and tidy tables. Efficiency – Slashing the manual workload associated with data extraction. Efficiency Accuracy – Extracting data with laser-like precision to ensure reliable information. Accuracy Document Flexibility – Handling diverse document types, from unstructured chaos to neat and tidy tables. Document Flexibility Building the Dream Team: Gen AI and AWS Bedrock We knew a one-size-fits-all approach wouldn't cut it. So, we assembled a dream team of technologies, with Gen AI and AWS Bedrock leading the charge. Here's how we tackled the challenge: with Gen AI with Gen AI Building a Fortress: The Power of AWS – We leveraged the mighty AWS cloud environment, utilizing AWS Bedrock services to construct a robust backend. This fortress provided a secure and scalable foundation for our custom-developed solutions. Document Parsing with Gen AI: The Brains of the Operation – Powered by AWS Bedrock, we built a custom-made document parser. This intelligent tool was like Sherlock Holmes for documents, analyzing their structure and content to identify and extract relevant data fields with pinpoint accuracy. Specialized Pipelines: Tailored for Every Document – We didn't believe in a "one size fits all" approach. Instead, we designed specialized data extraction pipelines for each document type, ensuring optimal performance and accuracy for every format, from asset valuation reports to real estate assessments. Advanced AI Models and Tools: The Superpower Squad – We assembled a league of extraordinary AI models and tools to achieve the best possible results. OpenSearch provided a search platform with flexibility and scalability, while FAISS facilitated the efficient retrieval of similar documents. Additionally, we leveraged the power of foundation models like Titan and Cohere, along with Retrieval-Augmented Generation (RAG) to take the extraction process to the next level. Integration with Scanned Documents: No Doc Left Behind – We knew scanned documents were a reality, so we integrated AWS Textract. This powerful tool extracts data from scanned documents with impressive accuracy, ensuring seamless processing of all document formats. Data Quality: Our Top Priority – Maintaining data accuracy was paramount. We implemented rigorous Data Quality (DQ) checks across the extracted data, employing filtering mechanisms to guarantee clean and reliable outputs. This ensured the client received trustworthy data, ready for further use. Building a Fortress: The Power of AWS – We leveraged the mighty AWS cloud environment, utilizing AWS Bedrock services to construct a robust backend. This fortress provided a secure and scalable foundation for our custom-developed solutions. Building a Fortress: Document Parsing with Gen AI: The Brains of the Operation – Powered by AWS Bedrock, we built a custom-made document parser. This intelligent tool was like Sherlock Holmes for documents, analyzing their structure and content to identify and extract relevant data fields with pinpoint accuracy. Document Parsing with Gen AI: Specialized Pipelines: Tailored for Every Document – We didn't believe in a "one size fits all" approach. Instead, we designed specialized data extraction pipelines for each document type, ensuring optimal performance and accuracy for every format, from asset valuation reports to real estate assessments. Specialized Pipelines: Advanced AI Models and Tools: The Superpower Squad – We assembled a league of extraordinary AI models and tools to achieve the best possible results. OpenSearch provided a search platform with flexibility and scalability, while FAISS facilitated the efficient retrieval of similar documents. Additionally, we leveraged the power of foundation models like Titan and Cohere, along with Retrieval-Augmented Generation (RAG) to take the extraction process to the next level. Advanced AI Models and Tools: Integration with Scanned Documents: No Doc Left Behind – We knew scanned documents were a reality, so we integrated AWS Textract. This powerful tool extracts data from scanned documents with impressive accuracy, ensuring seamless processing of all document formats. Integration with Scanned Documents: Data Quality: Our Top Priority – Maintaining data accuracy was paramount. We implemented rigorous Data Quality (DQ) checks across the extracted data, employing filtering mechanisms to guarantee clean and reliable outputs. This ensured the client received trustworthy data, ready for further use. Data Quality: By combining these elements, we created a comprehensive solution that addressed the client's specific needs for efficient and accurate data extraction from complex and varied documents. Quantifiable Success: The Numbers Don't Lie The impact of our Gen AI-powered solution was clear as day (and measurable!). Here's how Gen AI helped our client achieve significant improvements: Gen AI-powered solution Gen AI-powered solution Soaring Accuracy: 87% Across the Board – Our client craved data accuracy, and we delivered. Our solution achieved an impressive 87% accuracy rate across all document types. This meant the extracted data was reliable and ready for further analysis and use without extensive manual verification. Dramatic Reduction in Manual Effort: From Days to Hours – The time-consuming nature of manual data extraction was a major bottleneck for the client. Our solution streamlined the process, resulting in a staggering 700x reduction in manual effort. Imagine tasks that previously took days to complete, now achievable in a matter of hours. Think of the reallocated resources and the potential for increased productivity! That's a 700x time multiplier, folks. That's like shaving weeks off a project, freeing up your team to focus on higher-level tasks, strategic analysis, or even chasing that elusive work-life balance. Significant Cost Savings: A 4x Advantage – The efficiency gains brought about by automation also yielded substantial cost savings for the client. By eliminating the need for manual data extraction, the client achieved a 4x reduction in costs. These savings can be re-invested in further growth initiatives, expanding their service offerings, or even delighting their clients with lower fees. Soaring Accuracy: 87% Across the Board – Our client craved data accuracy, and we delivered. Our solution achieved an impressive 87% accuracy rate across all document types. This meant the extracted data was reliable and ready for further analysis and use without extensive manual verification. Soaring Accuracy: Dramatic Reduction in Manual Effort: From Days to Hours – The time-consuming nature of manual data extraction was a major bottleneck for the client. Our solution streamlined the process, resulting in a staggering 700x reduction in manual effort. Imagine tasks that previously took days to complete, now achievable in a matter of hours. Think of the reallocated resources and the potential for increased productivity! That's a 700x time multiplier, folks. That's like shaving weeks off a project, freeing up your team to focus on higher-level tasks, strategic analysis, or even chasing that elusive work-life balance. Dramatic Reduction in Manual Effort: Significant Cost Savings: A 4x Advantage – The efficiency gains brought about by automation also yielded substantial cost savings for the client. By eliminating the need for manual data extraction, the client achieved a 4x reduction in costs. These savings can be re-invested in further growth initiatives, expanding their service offerings, or even delighting their clients with lower fees. Significant Cost Savings: Beyond the Numbers: The Ripple Effect of Efficiency The benefits of our solution extended far beyond the numbers. Here's what our client experienced: Improved Decision-Making: With accurate and timely data at their fingertips, the client could confidently make data-driven decisions. Enhanced Client Service: Faster turnaround times and improved data quality translated into better service for their clients. Increased Scalability: The automation freed up resources, allowing the client to scale their operations and easily handle a larger volume of data. Improved Decision-Making: With accurate and timely data at their fingertips, the client could confidently make data-driven decisions. Improved Decision-Making: Enhanced Client Service: Faster turnaround times and improved data quality translated into better service for their clients. Enhanced Client Service: Increased Scalability: The automation freed up resources, allowing the client to scale their operations and easily handle a larger volume of data. Increased Scalability: The Takeaway: Gen AI and AWS Bedrock - Your Data Extraction Dream Team This project is a testament to Gen AI's and AWS Bedrock's power . By combining these innovative technologies, we were able to transform a tedious and error-prone process into a streamlined and efficient operation. to Gen AI's to Gen AI's and AWS Bedrock's power and AWS Bedrock's power If you're drowning in a sea of documents and struggling with data extraction, don't despair! We can help you build your own dream team. Indium's expertise in Gen AI and our understanding of your industry challenges can help you unlock the potential of your data and achieve remarkable results. So, are you ready to say goodbye to manual data extraction and hello to a world of efficiency and productivity? Let's chat! We're here to help you turn your data extraction woes into a thing of the past.

How Gen AI and AWS Bedrock Supercharged Real Estate Data Extraction  

কিভাবে Gen AI এবং AWS বেডরক সুপারচার্জ রিয়েল এস্টেট ডেটা এক্সট্রাকশন  

Wie Gen AI und AWS Bedrock die Datenextraktion im Immobilienbereich beschleunigten

Cómo Gen AI y AWS Bedrock potenciaron la extracción de datos inmobiliarios  

Comment Gen AI et AWS Bedrock ont dynamisé l'extraction de données immobilières  

कैसे जेन एआई और एडब्ल्यूएस बेडरॉक ने रियल एस्टेट डेटा निष्कर्षण को सुपरचार्ज किया

Gen AI と AWS Bedrock が不動産データ抽出をいかに強化したか

Gen AI와 AWS Bedrock이 부동산 데이터 추출을 강화하는 방법  

Como Gen AI e AWS Bedrock turbinaram a extração de dados imobiliários  

Как Gen AI и AWS Bedrock усовершенствовали извлечение данных о недвижимости  

Gen AI ve AWS Bedrock Gayrimenkul Veri Çıkarmayı Nasıl Güçlendirdi?  

Cách khai thác dữ liệu bất động sản tăng cường của Gen AI và AWS Bedrock  

Gen AI 和 AWS Bedrock 如何增强房地产数据提取

Supercavitating 'Em Steered Starship: Riding in Plasma Bubble

সুপারক্যাভিটেটিং 'এম স্টিয়ারড স্টারশিপ: এটি প্রতিরোধ করার চেষ্টা করার পরিবর্তে প্লাজমা পুনর্নির্দেশ করা

Superkavitierendes gesteuertes Raumschiff: Plasma umleiten statt verhindern

Supercavitando 'Em Steered Starship: redirigiendo el plasma en lugar de intentar prevenirlo

Supercavitation d'un vaisseau spatial dirigé : rediriger le plasma au lieu d'essayer de l'empêcher

सुपरकैविटेटिंग 'एम ने स्टारशिप को चलाया: इसे रोकने की कोशिश करने के बजाय प्लाज्मा को पुनर्निर्देशित करना

スーパーキャビテーション 操縦された宇宙船: プラズマを防ぐのではなく方向転換する

슈퍼캐비테이션 'Em 조종 우주선: 플라즈마를 방지하는 대신 방향을 바꾸다'

Supercavitando a nave estelar dirigida: redirecionando o plasma em vez de tentar evitá-lo

Суперкавитация управляемого звездолета: перенаправление плазмы вместо попыток ее предотвратить

Süper Kavitasyona Sahip Olanlar Yıldız Gemisini Yönlendirdi: Plazmayı Engellemeye Çalışmak Yerine Yönlendirmek

Supercavitation 'Em Steered Starship: Chuyển hướng plasma thay vì cố gắng ngăn chặn nó

超空泡操纵星舰：改变等离子体方向，而不是试图阻止它

At the SuperAI Conference in Singapore, HyperCycle unveiled HyperRing, a new addition to its line of products aimed at decentralizing AI technology. HyperRing, described as a high-end wearable ring, is designed to protect financial assets generated in the AI economy, merging technology with fashion elements. The HyperRing features a minimalist, battery-less, and sensor-free design, which aims to offer enhanced security compared to existing smart wearables. It utilizes NFC and MFA (multi-factor authentication) to protect digital assets from cyber threats. Toufi Saliba, CEO of HyperCycle, notes that the product is geared towards the growing sector of AI-enhanced wealth, with a focus on combining style with privacy and security features. HyperCycle’s strategy includes the use of advanced protocols such as TODA/IP and Earth64, facilitating what it calls an "Internet of AI". This network is designed to allow AI agents to conduct transactions and learn from each other independently, which could shift the current dynamics in AI interactions. The company’s initiatives also extend to HyperPG and HyperBox, aimed at enhancing AI-to-AI communication with the goal of faster and more effective learning algorithms. HyperCycle's emphasis on a decentralized AI network suggests a move away from traditional cloud computing and AI services towards a more scalable and secure infrastructure, contingent on network performance and user adoption. The introduction of HyperRing at the SuperAI conference reflects HyperCycle’s broader objectives to shape the future of AI-enabled transactions. The integration of decentralized protocols is intended to reduce dependence on centralized computing resources, potentially leading to a more efficient framework for AI interactions. The design of HyperRing, free from batteries and sensors, targets a specific market segment concerned with privacy issues. In today's environment of heightened digital surveillance, this approach could appeal to those seeking secure yet fashionable methods to manage digital assets. Final Thoughts HyperCycle’s approach with HyperRing seems attuned to emerging trends in AI and wearable technology. The product’s security features, combined with its focus on privacy, may appeal to both technologically adept individuals and privacy advocates. As the digital environment evolves, products like HyperRing could influence consumer expectations and set new standards in wearable technology. Success for HyperCycle will likely hinge on its ability to integrate these innovations effectively into everyday user experiences, making the technology both advanced and user-friendly. Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program. HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. At the SuperAI Conference in Singapore, HyperCycle unveiled HyperRing, a new addition to its line of products aimed at decentralizing AI technology. HyperRing, described as a high-end wearable ring, is designed to protect financial assets generated in the AI economy, merging technology with fashion elements. The HyperRing features a minimalist, battery-less, and sensor-free design, which aims to offer enhanced security compared to existing smart wearables. It utilizes NFC and MFA (multi-factor authentication) to protect digital assets from cyber threats. Toufi Saliba, CEO of HyperCycle, notes that the product is geared towards the growing sector of AI-enhanced wealth, with a focus on combining style with privacy and security features. HyperCycle’s strategy includes the use of advanced protocols such as TODA/IP and Earth64, facilitating what it calls an "Internet of AI". This network is designed to allow AI agents to conduct transactions and learn from each other independently, which could shift the current dynamics in AI interactions. The company’s initiatives also extend to HyperPG and HyperBox, aimed at enhancing AI-to-AI communication with the goal of faster and more effective learning algorithms. HyperCycle's emphasis on a decentralized AI network suggests a move away from traditional cloud computing and AI services towards a more scalable and secure infrastructure, contingent on network performance and user adoption. The introduction of HyperRing at the SuperAI conference reflects HyperCycle’s broader objectives to shape the future of AI-enabled transactions. The integration of decentralized protocols is intended to reduce dependence on centralized computing resources, potentially leading to a more efficient framework for AI interactions. The design of HyperRing, free from batteries and sensors, targets a specific market segment concerned with privacy issues. In today's environment of heightened digital surveillance, this approach could appeal to those seeking secure yet fashionable methods to manage digital assets. Final Thoughts Final Thoughts HyperCycle’s approach with HyperRing seems attuned to emerging trends in AI and wearable technology. The product’s security features, combined with its focus on privacy, may appeal to both technologically adept individuals and privacy advocates. As the digital environment evolves, products like HyperRing could influence consumer expectations and set new standards in wearable technology. Success for HyperCycle will likely hinge on its ability to integrate these innovations effectively into everyday user experiences, making the technology both advanced and user-friendly. Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program. HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program . HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. Vested Interest Disclosure: business blogging program business blogging program

HyperCycle Launches New Security-First Smart Wearable at SuperAI Conference

সুপারএআই কনফারেন্সে হাইপারসাইকেল লঞ্চ করেছে নতুন নিরাপত্তা-প্রথম স্মার্ট পরিধানযোগ্য

HyperCycle stellt auf der SuperAI-Konferenz ein neues, sicherheitsorientiertes Smart Wearable vor

HyperCycle lanza un nuevo dispositivo portátil inteligente que prioriza la seguridad en la conferencia SuperAI

HyperCycle lance un nouveau portable intelligent axé sur la sécurité lors de la conférence SuperAI

हाइपरसाइकल ने सुपरएआई कॉन्फ्रेंस में नया सुरक्षा-प्रथम स्मार्ट वियरेबल लॉन्च किया

HyperCycle が SuperAI カンファレンスでセキュリティ重視の新型スマートウェアラブルを発表

HyperCycle, SuperAI 컨퍼런스에서 새로운 보안 우선 스마트 웨어러블 출시

HyperCycle lança novo wearable inteligente que prioriza a segurança na SuperAI Conference

HyperCycle представляет новое интеллектуальное носимое устройство, ориентированное на безопасность, на конференции SuperAI

HyperCycle, SuperAI Konferansında Güvenliği Ön Plana Çıkaran Yeni Akıllı Giyilebilir Cihazını Piyasaya Sürüyor

HyperCycle ra mắt thiết bị đeo thông minh đầu tiên về bảo mật mới tại Hội nghị SuperAI

HyperCycle 在 SuperAI 大会上推出全新安全第一智能可穿戴设备

Superposition: Pioneering High Fidelity DeFi on Extremely Performative Blockchains

সুপারপজিশন: অত্যন্ত পারফরমেটিভ ব্লকচেইনে অগ্রগামী উচ্চ বিশ্বস্ততা ডিফাই

Superposition: Pionierarbeit für High Fidelity DeFi auf extrem performanten Blockchains

Superposición: pioneros en DeFi de alta fidelidad en cadenas de bloques extremadamente performativas

Superposition : une DeFi haute fidélité pionnière sur des blockchains extrêmement performantes

सुपरपोजिशन: अत्यंत प्रदर्शनकारी ब्लॉकचेन पर अग्रणी हाई फिडेलिटी डीफाई

重ね合わせ: 極めて高性能なブロックチェーン上で高忠実度の DeFi を先駆的に実現

중첩: 매우 성능이 뛰어난 블록체인에서 선구적인 고성능 DeFi

Superposição: Pioneirismo em DeFi de alta fidelidade em blockchains extremamente performáticos

Суперпозиция: новаторский высокоточный DeFi на чрезвычайно производительных блокчейнах

Süperpozisyon: Son Derece Performanslı Blok Zincirlerinde Yüksek Kaliteli DeFi'de Öncülük

Sự chồng chất: DeFi tiên phong có độ trung thực cao trên các chuỗi khối cực kỳ hiệu quả

叠加：在性能卓越的区块链上开创高保真 DeFi

Author:
(1) Mingda Chen. Table of Links Abstract


Acknowledgements


1 INTRODUCTION


1.1 Overview


1.2 Contributions


2 BACKGROUND


2.1 Self-Supervised Language Pretraining


2.2 Naturally-Occurring Data Structures


2.3 Sentence Variational Autoencoder


2.4 Summary


3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING


3.1 Improving Language Representation Learning via Sentence Ordering Prediction


3.2 Improving In-Context Few-Shot Learning via Self-Supervised Training


3.3 Summary


4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA


4.1 Learning Entity Representations from Hyperlinks


4.2 Learning Discourse-Aware Sentence Representations from Document Structures


4.3 Learning Concept Hierarchies from Document Categories


4.4 Summary


5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY


5.1 Disentangling Semantics and Syntax in Sentence Representations


5.2 Controllable Paraphrase Generation with a Syntactic Exemplar


5.3 Summary


6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS


6.1 Long-Form Data-to-Text Generation


6.2 Long-Form Text Summarization


6.3 Story Generation with Constraints


6.4 Summary


7 CONCLUSION


APPENDIX A - APPENDIX TO CHAPTER 3


APPENDIX B - APPENDIX TO CHAPTER 6


BIBLIOGRAPHY 2.3 Sentence Variational Autoencoder Variational autoencoders are models that combine latent-variable modeling and neural networks. As a type of variational autoencoders, sentence variational autoencoders (SVAEs) seek to model a sentence through latent variables. The use of latent variables allows for design choices that reflect certain aspects of a sentence: e.g., sentiment and formality, leading to controllable and interpretable neural architectures. Below we briefly review the related work. 2.3.1 Related Work SVAEs with a single latent variable often assumes that the latent variable follows Gaussian distributions, where researchers primarily focus on improving the SVAEs capabilities in language modeling (as measured by perplexities) and generating from interpolated samples from latent distributions (Bowman et al., 2016). Relevant work studies the effect of different latent distributions, including von Mises-Fisher distributions (Xu and Durrett, 2018), Gaussian mixtures (Ding and Gimpel, 2021), Gumbel-softmax distributions (Zhou and Neubig, 2017), discrete variables (Wiseman et al., 2018; Deng et al., 2018; Ziegler and Rush, 2019; Stratos and Wiseman, 2020; Jin et al., 2020a), piecewise constant distributions (Serban et al., 2017), samplebased (Fang et al., 2019) and flow-based distributions (Ma et al., 2019; Setiawan et al., 2020; Ding and Gimpel, 2021). Apart from language modeling, researchers have used SVAEs for machine translations (Zhang et al., 2016; Schulz et al., 2018; Eikema and Aziz, 2019; Ma et al., 2019; Calixto et al., 2019; Setiawan et al., 2020), relation extraction (Marcheggiani and Titov, 2016), dependency parsing (Corro and Titov, 2019), word representations (Rios et al., 2018), dialogue generation (Shen et al., 2017b; Bahuleyan et al., 2018; Shen et al., 2018b), text classification (Ding and Gimpel, 2019; Gururangan et al., 2019; Jin et al., 2020a), and question generation (Bahuleyan et al., 2018). Increasing attention has also been devoted to interpretable representation learning (Bastings et al., 2019; Zhou et al., 2020; Goyal et al., 2020; Cheng et al., 2020; Mercatali and Freitas, 2021; Vishnubhotla et al., 2021) and controllable generation (e.g., controling sentiment (Hu et al., 2017; Shen et al., 2017a) or formality (Ficler and Goldberg, 2017)). 2.3.2 Formal Preliminaries Below we derive the training objectives for sentence variational autoencoders using Gaussian and vMF distributions. These materials will be used in Section 5.1 and Section 5.2. where KL divergence is a distance measure between two probability distributions (Kullback and Leibler, 1951) and we have introduced the variational posterior q parametrized by new parameters φ. q is referred to as an “inference model” as it encodes an input into the latent space. We also have the generative model probabilities p parametrized by θ. The parameters are trained in a way that reflects a classical autoencoder framework: encode the input into a latent space, decode the latent space to reconstruct the input. These models are therefore referred to as “variational autoencoders”. The lower bound (also known as the evidence lower bound (ELBO)) consists of two terms: reconstruction loss and KL divergence. The KL divergence term provides a regularizing effect during learning by ensuring that the learned posterior remains close to the prior over the latent variables. This paper is available on arxiv under CC 4.0 license. Author: (1) Mingda Chen. Author: Author: (1) Mingda Chen. Table of Links Abstract Acknowledgements 1 INTRODUCTION 1.1 Overview 1.2 Contributions 2 BACKGROUND 2.1 Self-Supervised Language Pretraining 2.2 Naturally-Occurring Data Structures 2.3 Sentence Variational Autoencoder 2.4 Summary 3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING 3.1 Improving Language Representation Learning via Sentence Ordering Prediction 3.2 Improving In-Context Few-Shot Learning via Self-Supervised Training 3.3 Summary 4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA 4.1 Learning Entity Representations from Hyperlinks 4.2 Learning Discourse-Aware Sentence Representations from Document Structures 4.3 Learning Concept Hierarchies from Document Categories 4.4 Summary 5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY 5.1 Disentangling Semantics and Syntax in Sentence Representations 5.2 Controllable Paraphrase Generation with a Syntactic Exemplar 5.3 Summary 6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS 6.1 Long-Form Data-to-Text Generation 6.2 Long-Form Text Summarization 6.3 Story Generation with Constraints 6.4 Summary 7 CONCLUSION APPENDIX A - APPENDIX TO CHAPTER 3 APPENDIX B - APPENDIX TO CHAPTER 6 BIBLIOGRAPHY Abstract Abstract Abstract Acknowledgements Acknowledgements Acknowledgements 1 INTRODUCTION 1 INTRODUCTION 1 INTRODUCTION 1 INTRODUCTION 1.1 Overview 1.1 Overview 1.1 Overview 1.2 Contributions 1.2 Contributions 1.2 Contributions 2 BACKGROUND 2 BACKGROUND 2 BACKGROUND 2 BACKGROUND 2.1 Self-Supervised Language Pretraining 2.1 Self-Supervised Language Pretraining 2.1 Self-Supervised Language Pretraining 2.2 Naturally-Occurring Data Structures 2.2 Naturally-Occurring Data Structures 2.2 Naturally-Occurring Data Structures 2.3 Sentence Variational Autoencoder 2.3 Sentence Variational Autoencoder 2.3 Sentence Variational Autoencoder 2.4 Summary 2.4 Summary 2.4 Summary 3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING 3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING 3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING 3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING 3.1 Improving Language Representation Learning via Sentence Ordering Prediction 3.1 Improving Language Representation Learning via Sentence Ordering Prediction 3.1 Improving Language Representation Learning via Sentence Ordering Prediction 3.2 Improving In-Context Few-Shot Learning via Self-Supervised Training 3.2 Improving In-Context Few-Shot Learning via Self-Supervised Training 3.2 Improving In-Context Few-Shot Learning via Self-Supervised Training 3.3 Summary 3.3 Summary 3.3 Summary 4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA 4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA 4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA 4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA 4.1 Learning Entity Representations from Hyperlinks 4.1 Learning Entity Representations from Hyperlinks 4.1 Learning Entity Representations from Hyperlinks 4.2 Learning Discourse-Aware Sentence Representations from Document Structures 4.2 Learning Discourse-Aware Sentence Representations from Document Structures 4.2 Learning Discourse-Aware Sentence Representations from Document Structures 4.3 Learning Concept Hierarchies from Document Categories 4.3 Learning Concept Hierarchies from Document Categories 4.3 Learning Concept Hierarchies from Document Categories 4.4 Summary 4.4 Summary 4.4 Summary 5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY 5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY 5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY 5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY 5.1 Disentangling Semantics and Syntax in Sentence Representations 5.1 Disentangling Semantics and Syntax in Sentence Representations 5.1 Disentangling Semantics and Syntax in Sentence Representations 5.2 Controllable Paraphrase Generation with a Syntactic Exemplar 5.2 Controllable Paraphrase Generation with a Syntactic Exemplar 5.2 Controllable Paraphrase Generation with a Syntactic Exemplar 5.3 Summary 5.3 Summary 5.3 Summary 6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS 6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS 6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS 6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS 6.1 Long-Form Data-to-Text Generation 6.1 Long-Form Data-to-Text Generation 6.1 Long-Form Data-to-Text Generation 6.2 Long-Form Text Summarization 6.2 Long-Form Text Summarization 6.2 Long-Form Text Summarization 6.3 Story Generation with Constraints 6.3 Story Generation with Constraints 6.3 Story Generation with Constraints 6.4 Summary 6.4 Summary 6.4 Summary 7 CONCLUSION 7 CONCLUSION 7 CONCLUSION 7 CONCLUSION APPENDIX A - APPENDIX TO CHAPTER 3 APPENDIX A - APPENDIX TO CHAPTER 3 APPENDIX A - APPENDIX TO CHAPTER 3 APPENDIX B - APPENDIX TO CHAPTER 6 APPENDIX B - APPENDIX TO CHAPTER 6 APPENDIX B - APPENDIX TO CHAPTER 6 BIBLIOGRAPHY BIBLIOGRAPHY BIBLIOGRAPHY 2.3 Sentence Variational Autoencoder Variational autoencoders are models that combine latent-variable modeling and neural networks. As a type of variational autoencoders, sentence variational autoencoders (SVAEs) seek to model a sentence through latent variables. The use of latent variables allows for design choices that reflect certain aspects of a sentence: e.g., sentiment and formality, leading to controllable and interpretable neural architectures. Below we briefly review the related work. 2.3.1 Related Work SVAEs with a single latent variable often assumes that the latent variable follows Gaussian distributions, where researchers primarily focus on improving the SVAEs capabilities in language modeling (as measured by perplexities) and generating from interpolated samples from latent distributions (Bowman et al., 2016). Relevant work studies the effect of different latent distributions, including von Mises-Fisher distributions (Xu and Durrett, 2018), Gaussian mixtures (Ding and Gimpel, 2021), Gumbel-softmax distributions (Zhou and Neubig, 2017), discrete variables (Wiseman et al., 2018; Deng et al., 2018; Ziegler and Rush, 2019; Stratos and Wiseman, 2020; Jin et al., 2020a), piecewise constant distributions (Serban et al., 2017), samplebased (Fang et al., 2019) and flow-based distributions (Ma et al., 2019; Setiawan et al., 2020; Ding and Gimpel, 2021). Apart from language modeling, researchers have used SVAEs for machine translations (Zhang et al., 2016; Schulz et al., 2018; Eikema and Aziz, 2019; Ma et al., 2019; Calixto et al., 2019; Setiawan et al., 2020), relation extraction (Marcheggiani and Titov, 2016), dependency parsing (Corro and Titov, 2019), word representations (Rios et al., 2018), dialogue generation (Shen et al., 2017b; Bahuleyan et al., 2018; Shen et al., 2018b), text classification (Ding and Gimpel, 2019; Gururangan et al., 2019; Jin et al., 2020a), and question generation (Bahuleyan et al., 2018). Increasing attention has also been devoted to interpretable representation learning (Bastings et al., 2019; Zhou et al., 2020; Goyal et al., 2020; Cheng et al., 2020; Mercatali and Freitas, 2021; Vishnubhotla et al., 2021) and controllable generation (e.g., controling sentiment (Hu et al., 2017; Shen et al., 2017a) or formality (Ficler and Goldberg, 2017)). 2.3.2 Formal Preliminaries Below we derive the training objectives for sentence variational autoencoders using Gaussian and vMF distributions. These materials will be used in Section 5.1 and Section 5.2. where KL divergence is a distance measure between two probability distributions (Kullback and Leibler, 1951) and we have introduced the variational posterior q parametrized by new parameters φ. q is referred to as an “inference model” as it encodes an input into the latent space. We also have the generative model probabilities p parametrized by θ. The parameters are trained in a way that reflects a classical autoencoder framework: encode the input into a latent space, decode the latent space to reconstruct the input. These models are therefore referred to as “variational autoencoders”. The lower bound (also known as the evidence lower bound (ELBO)) consists of two terms: reconstruction loss and KL divergence. The KL divergence term provides a regularizing effect during learning by ensuring that the learned posterior remains close to the prior over the latent variables. This paper is available on arxiv under CC 4.0 license. This paper is available on arxiv under CC 4.0 license. available on arxiv

Leveraging Natural Supervision for Language Representation: Sentence Variational Autoencoder

Author:
(1) Mingda Chen. Table of Links Abstract


Acknowledgements


1 INTRODUCTION


1.1 Overview


1.2 Contributions


2 BACKGROUND


2.1 Self-Supervised Language Pretraining


2.2 Naturally-Occurring Data Structures


2.3 Sentence Variational Autoencoder


2.4 Summary


3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING


3.1 Improving Language Representation Learning via Sentence Ordering Prediction


3.2 Improving In-Context Few-Shot Learning via Self-Supervised Training


3.3 Summary


4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA


4.1 Learning Entity Representations from Hyperlinks


4.2 Learning Discourse-Aware Sentence Representations from Document Structures


4.3 Learning Concept Hierarchies from Document Categories


4.4 Summary


5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY


5.1 Disentangling Semantics and Syntax in Sentence Representations


5.2 Controllable Paraphrase Generation with a Syntactic Exemplar


5.3 Summary


6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS


6.1 Long-Form Data-to-Text Generation


6.2 Long-Form Text Summarization


6.3 Story Generation with Constraints


6.4 Summary


7 CONCLUSION


APPENDIX A - APPENDIX TO CHAPTER 3


APPENDIX B - APPENDIX TO CHAPTER 6


BIBLIOGRAPHY ACKNOWLEDGEMENTS Like all great travellers, I have seen more than I remember, and remember more than I have seen. – Benjamin Disraeli The Ph.D. journey is an adventure mixed with daunting challenges, unanticipated bafflements, and instant delights. Many people have guided me through the challenges, clarified my confusion, and shared my happiness. I am enormously grateful for their help along the journey. First, I want to thank my advisor Kevin Gimpel for the technical insight and research philosophy throughout these years. He was always knowledgeable about everything we worked on, meticulous about every word we wrote on papers, and patient about my mistakes. The work in this thesis would not be possible without his positive, steady influence. I thank the rest of my thesis committee: Karen Livescu, Sam Wiseman, and Luke Zettlemoyer, for being generous with their time and insight. I also thank Karl Stratos for his guidance. I thank my fellow students at Toyota Technological Institute at Chicago and the University of Chicago, especially Qingming Tang for the technical (and nontechnical) conversations, Bumeng Zhuo for the fun activities during weekends, and Zewei Chu for the bike rides at the lakefront in Chicago. I am also grateful to my fellow interns and mentors at Google and Facebook. Lastly, I would like to thank my family for inspiring my interest in learning, encouraging me to apply to graduate school, and being supportive and interested in listening to my research ramblings. This paper is available on arxiv under CC 4.0 license. Author: (1) Mingda Chen. Author: Author: (1) Mingda Chen. Table of Links Abstract Acknowledgements 1 INTRODUCTION 1.1 Overview 1.2 Contributions 2 BACKGROUND 2.1 Self-Supervised Language Pretraining 2.2 Naturally-Occurring Data Structures 2.3 Sentence Variational Autoencoder 2.4 Summary 3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING 3.1 Improving Language Representation Learning via Sentence Ordering Prediction 3.2 Improving In-Context Few-Shot Learning via Self-Supervised Training 3.3 Summary 4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA 4.1 Learning Entity Representations from Hyperlinks 4.2 Learning Discourse-Aware Sentence Representations from Document Structures 4.3 Learning Concept Hierarchies from Document Categories 4.4 Summary 5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY 5.1 Disentangling Semantics and Syntax in Sentence Representations 5.2 Controllable Paraphrase Generation with a Syntactic Exemplar 5.3 Summary 6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS 6.1 Long-Form Data-to-Text Generation 6.2 Long-Form Text Summarization 6.3 Story Generation with Constraints 6.4 Summary 7 CONCLUSION APPENDIX A - APPENDIX TO CHAPTER 3 APPENDIX B - APPENDIX TO CHAPTER 6 BIBLIOGRAPHY Abstract Abstract Abstract Acknowledgements Acknowledgements Acknowledgements 1 INTRODUCTION 1 INTRODUCTION 1 INTRODUCTION 1 INTRODUCTION 1.1 Overview 1.1 Overview 1.1 Overview 1.2 Contributions 1.2 Contributions 1.2 Contributions 2 BACKGROUND 2 BACKGROUND 2 BACKGROUND 2 BACKGROUND 2.1 Self-Supervised Language Pretraining 2.1 Self-Supervised Language Pretraining 2.1 Self-Supervised Language Pretraining 2.2 Naturally-Occurring Data Structures 2.2 Naturally-Occurring Data Structures 2.2 Naturally-Occurring Data Structures 2.3 Sentence Variational Autoencoder 2.3 Sentence Variational Autoencoder 2.3 Sentence Variational Autoencoder 2.4 Summary 2.4 Summary 2.4 Summary 3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING 3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING 3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING 3 IMPROVING SELF-SUPERVISION FOR LANGUAGE PRETRAINING 3.1 Improving Language Representation Learning via Sentence Ordering Prediction 3.1 Improving Language Representation Learning via Sentence Ordering Prediction 3.1 Improving Language Representation Learning via Sentence Ordering Prediction 3.2 Improving In-Context Few-Shot Learning via Self-Supervised Training 3.2 Improving In-Context Few-Shot Learning via Self-Supervised Training 3.2 Improving In-Context Few-Shot Learning via Self-Supervised Training 3.3 Summary 3.3 Summary 3.3 Summary 4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA 4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA 4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA 4 LEARNING SEMANTIC KNOWLEDGE FROM WIKIPEDIA 4.1 Learning Entity Representations from Hyperlinks 4.1 Learning Entity Representations from Hyperlinks 4.1 Learning Entity Representations from Hyperlinks 4.2 Learning Discourse-Aware Sentence Representations from Document Structures 4.2 Learning Discourse-Aware Sentence Representations from Document Structures 4.2 Learning Discourse-Aware Sentence Representations from Document Structures 4.3 Learning Concept Hierarchies from Document Categories 4.3 Learning Concept Hierarchies from Document Categories 4.3 Learning Concept Hierarchies from Document Categories 4.4 Summary 4.4 Summary 4.4 Summary 5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY 5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY 5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY 5 DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY 5.1 Disentangling Semantics and Syntax in Sentence Representations 5.1 Disentangling Semantics and Syntax in Sentence Representations 5.1 Disentangling Semantics and Syntax in Sentence Representations 5.2 Controllable Paraphrase Generation with a Syntactic Exemplar 5.2 Controllable Paraphrase Generation with a Syntactic Exemplar 5.2 Controllable Paraphrase Generation with a Syntactic Exemplar 5.3 Summary 5.3 Summary 5.3 Summary 6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS 6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS 6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS 6 TAILORING TEXTUAL RESOURCES FOR EVALUATION TASKS 6.1 Long-Form Data-to-Text Generation 6.1 Long-Form Data-to-Text Generation 6.1 Long-Form Data-to-Text Generation 6.2 Long-Form Text Summarization 6.2 Long-Form Text Summarization 6.2 Long-Form Text Summarization 6.3 Story Generation with Constraints 6.3 Story Generation with Constraints 6.3 Story Generation with Constraints 6.4 Summary 6.4 Summary 6.4 Summary 7 CONCLUSION 7 CONCLUSION 7 CONCLUSION 7 CONCLUSION APPENDIX A - APPENDIX TO CHAPTER 3 APPENDIX A - APPENDIX TO CHAPTER 3 APPENDIX A - APPENDIX TO CHAPTER 3 APPENDIX B - APPENDIX TO CHAPTER 6 APPENDIX B - APPENDIX TO CHAPTER 6 APPENDIX B - APPENDIX TO CHAPTER 6 BIBLIOGRAPHY BIBLIOGRAPHY BIBLIOGRAPHY ACKNOWLEDGEMENTS Like all great travellers, I have seen more than I remember, and remember more than I have seen. Like all great travellers, I have seen more than I remember, and remember more than I have seen. – Benjamin Disraeli The Ph.D. journey is an adventure mixed with daunting challenges, unanticipated bafflements, and instant delights. Many people have guided me through the challenges, clarified my confusion, and shared my happiness. I am enormously grateful for their help along the journey. First, I want to thank my advisor Kevin Gimpel for the technical insight and research philosophy throughout these years. He was always knowledgeable about everything we worked on, meticulous about every word we wrote on papers, and patient about my mistakes. The work in this thesis would not be possible without his positive, steady influence. I thank the rest of my thesis committee: Karen Livescu, Sam Wiseman, and Luke Zettlemoyer, for being generous with their time and insight. I also thank Karl Stratos for his guidance. I thank my fellow students at Toyota Technological Institute at Chicago and the University of Chicago, especially Qingming Tang for the technical (and nontechnical) conversations, Bumeng Zhuo for the fun activities during weekends, and Zewei Chu for the bike rides at the lakefront in Chicago. I am also grateful to my fellow interns and mentors at Google and Facebook. Lastly, I would like to thank my family for inspiring my interest in learning, encouraging me to apply to graduate school, and being supportive and interested in listening to my research ramblings. This paper is available on arxiv under CC 4.0 license. This paper is available on arxiv under CC 4.0 license. available on arxiv

Super

about.superapp.id

501-1K employees

Since 2018

COMPANY RANKING

SUPER

EVERGREEN INDEX #673

Super WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!

Super

about.superapp.id

501-1K employees

Since 2018

COMPANY RANKING

SUPER

EVERGREEN INDEX #673

RELATED COMPANIESRANK

STORIES ABOUT SUPER

Super WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!