Introduction to word2vec embeddings and use cases Photo by on Dmitry Ratushny Unsplash Natural language processing (NLP) is an area of computer science and that is _k_nown to be concerned with the interaction between computer and hum_a_ns in n_a_tural language. The goal is to enable the systems to fully understand _v_arious language as well as we do. It is the driving force behind like v_i_rtual assistants, speech recognition, machine translation, sentiment anal_y_sis, automatic text summarization, and much more. We’ll be working on word embedding technique called Word2Vec using Gensim framework in this post. artificial intelligence NLP products/techniques a Word Embeddings… what!! Word Embedding is an NLP technique, capable of capturing the context of a word in a document, semantic and syntactic similarity, relation with other words, etc. In general, they are vector representations of a particular word. Having said that what follows is the techniques to create Word Embeddings. There are many techniques to create Word Embeddings. Some of the popular ones are: Binary Encoding. TF Encoding. TF-IDF Encoding. Latent Semantic Analysis Encoding. Word2Vec Embedding. We’ll discuss the different embedding techniques on future posts, for now, we’ll stick with Word2Vec Embedding. Intro to Word2Vec Embedding is one of the most widely used models to produce . These models are shallow, two-layer that are trained to reconstruct linguistic contexts of words. Word2Vec can be implemented in two ways, one is Skip Gram and other is Common Bag Of Words (CBOW) Word2vec word embeddings neural networks Continuous Bag Of Words (CBOW) is learning to predict the word by the context. Here the input will be the context and output will be the target word. The limit on the number of words in each context is determined by a parameter called “ ”. CBOW #neighboring words window size Example: The quick brown fox jumps over the lazy dog #yes the same example :-) Model: CBOW INPUT Layer: White box content TARGET Layer: blue box word Window Size: 5 Skip Gram is learning to predict the context by the word. Here the input will be the word and output will be the target context . The limit on the number of words in each context is determined by a parameter called “ ”. Skip Gram #neighboring words window size Example: The quick brown fox jumps over the lazy dog #yes the same example :-) Model: Skip Gram INPUT Layer: blue box word TARGET Layer: White box content Window Size: 5 Behind the scenes As discussed above, we’ll be using two-layer . For this model, the input later will be the context respect to target word followed by the hidden layer which constructs the relationship lastly the target layer with the target word. neural networks After training the model, each word in the corpus will have its own vector embeddings with respect to the context and meaning. Now we can use for mapping the word embeddings, which might give us a clear picture of how relationships are made and vectors are assigned. Matplotlib Word2Vec Embeddings INPUT CORPUS 1. this is the first sentence for word2vec 2. this is the second sentence 3. yet another sentence 4. one more sentence5. and the final sentence As we can see similar words are mapped nearby based on their context like ‘first’ & ‘second’, ‘one’ & ‘another’ and the word ‘sentence’ is separated from the clusters as it is nowhere similar to any of the other words. From here we can use these embeddings to have similar words, sentence or documents with the same content and the list goes on… Literally everywhere!! That’s it for explaining things, I believe have got some understanding about word2vec. If not, don’t worry! you can get a clear idea after going through the example below. let’s dive into some python 🐍. you Let’s add Some Python As we discussed earlier, we’ll be implementing word2vec using Gensim framework in python. is a robust and toolkit implemented in . It uses , and optionally for performance. Gensim open-source vector space modeling topic modeling Python NumPy SciPy Cython Here we have imported the requirements, next we’ll be defining out text corpus. In this step, We are defining our . Word2vec model Here, is the dimensionality of the vector higher the size denser the embeddings( ideally must be lower than the vocab length. Using a higher dimensionality than vocabulary size would more-or-less guarantee ‘overfitting’.) size size Words below the frequency are dropped before training occurs(as we have few lines of input corpus, we are taking every word). min_count Corpus is added to vocab for training and training is done. PCA model is used to reduce the dimensioned vector for each word in our vocab to a 2d vector(we are doing this for plotting/visualize our results). n We’ll be using scatter plot in matplotlib for plotting the word embeddings, As we can see, the word embeddings are mapped relative to each other. This result is had, by using the pre-trained model for simplicity basic model is discussed. Original model can be found . here Let’s find some similarity Using this word embeddings we can find similarity between the words in our corpus. >>>model_1.most_similar(positive=[‘first’], topn=1) [('second', 0.8512464761734009)] The most_similar function is to find similar words in our embeddings to the target word. >>>model_1.similarity('one', 'another') 0.80782 Here we found the similarity between the two words in our embeddings. Like this, there are many useful functions to work with. They can be found . here We end this here, hope I’ve given some introduction to the word2vec embeddings. Check the other works . here Lol, if you think so we are on the same page. Let’s connect , , . Medium Linkedin Facebook
![What Are Convolution Neural Networks? [ELI5]](https://hackernoon.imgix.net/images/69s32rn.jpg?auto=format&fit=max&w=3840)
