paint-brush
JINA EMBEDDINGS 2: 8192-Token General-Purpose Text Embeddings: Conclusion & Referencesby@escholar

JINA EMBEDDINGS 2: 8192-Token General-Purpose Text Embeddings: Conclusion & References

tldt arrow

Too Long; Didn't Read

Text embedding models have emerged as powerful tools for transforming sentences into fixedsized feature vectors that encapsulate semantic information.
featured image - JINA EMBEDDINGS 2: 8192-Token General-Purpose Text Embeddings: Conclusion & References
EScholar: Electronic Academic Papers for Scholars HackerNoon profile picture

This paper is available on arxiv under CC 4.0 license.

Authors:

(1) Michael Günther, michael.guenther;

(2) Jackmin Ong, jackmin.ong;

(3) Isabelle Mohr, isabelle.mohr;

(4) Alaeddine Abdessalem, alaeddine.abdessalem;

(5) Tanguy Abel, tanguy.abel;

(6) Mohammad Kalim Akram, kalim.akram;

(7) Susana Guzman, susana.guzman;

(8) Georgios Mastrapas, georgios.mastrapas;

(9) Saba Sturua, saba.sturua;

(10) Bo Wang, bo.wang;

(11) Maximilian Werk, maximilian.werk;

(12) Nan Wang, nan.wang;

(13) Han Xiao, han.xiao}@jina.ai.

7 Conclusion

We have introduced Jina Embeddings v2, a novel embedding model based on a modified BERT architecture. This model eschews positional embeddings and instead employs bi-directional ALiBi slopes to capture positional information. By training a series of embedding models with this innovative architecture on the Web document corpus C4 and subsequently fine-tuning them, we have enabled the encoding of the semantics of both short and long textual values into meaningful vector representations. This effort has produced a new suite of open-source embedding models capable of encoding texts containing up to 8192 tokens. These embeddings signify a 16x increase in the maximum sequence length compared to leading open-source embedding models. Additionally, our model suite exhibits competitive performance on the MTEB benchmark. We also demonstrate how utilizing extended sequence lengths can offer our models an advantage over those without such capabilities.

References

Nils Reimers and Iryna Gurevych. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Lan-guage Processing (EMNLP-IJCNLP), pages 3982– 3992, 2019.


Ofir Press, Noah A. Smith, and Mike Lewis. Train short, test long: Attention with linear biases enables input length extrapolation, 2022.


Michael Günther, Louis Milliken, Jonathan Geuter, Georgios Mastrapas, Bo Wang, and Han Xiao. Jina embeddings: A novel set of high-performance sentence embedding models. arXiv preprint arXiv:2307.11224, 2023.


Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. Text embeddings by weaklysupervised contrastive pre-training. arXiv preprint arXiv:2212.03533, 2022.


Scott Deerwester, Susan T. Dumais, George W. Furnas, Thomas K. Landauer, and Richard Harshman. Indexing by latent semantic analysis. Journal of the American Society for Information Science, 41(6):391–407, 1990.


David Blei, Andrew Ng, and Michael Jordan. Latent dirichlet allocation. In T. Dietterich, S. Becker, and Z. Ghahramani, editors, Advances in Neural Information Processing Systems, volume 14. MIT Press, 2001. URL https://proceedings. neurips.cc/paper_files/paper/2001/file/ 296472c9542ad4d4788d543508116cbc-Paper. pdf.


Tianyu Gao, Xingcheng Yao, and Danqi Chen. Simcse: Simple contrastive learning of sentence embeddings, 2022.


Luyu Gao and Jamie Callan. Condenser: a pre-training architecture for dense retrieval, 2021.


Shitao Xiao, Zheng Liu, Yingxia Shao, and Zhao Cao. Retromae: Pre-training retrieval-oriented language models via masked auto-encoder, 2022.


Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. Towards general text embeddings with multi-stage contrastive learning, 2023.


Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava, and Iryna Gurevych. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models, 2021.


Niklas Muennighoff, Nouamane Tazi, Loïc Magne, and Nils Reimers. Mteb: Massive text embedding benchmark, 2023.


Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding, 2019.


Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized bert pretraining approach, 2019a.


Yann N. Dauphin, Angela Fan, Michael Auli, and David Grangier. Language modeling with gated convolutional networks. CoRR, abs/1612.08083, 2016. URL http://arxiv.org/abs/1612.08083.


Noam Shazeer. GLU variants improve transformer. CoRR, abs/2002.05202, 2020. URL https://arxiv. org/abs/2002.05202.


Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. CoRR, abs/1706.03762, 2017. URL http: //arxiv.org/abs/1706.03762.


Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. Megatron-lm: Training multi-billion parameter language models using model parallelism. CoRR, abs/1909.08053, 2019. URL http://arxiv.org/ abs/1909.08053.


Toan Q. Nguyen and Julian Salazar. Transformers without tears: Improving the normalization of selfattention. CoRR, abs/1910.05895, 2019. URL http://arxiv.org/abs/1910.05895.


Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 21(1): 5485–5551, 2020.


Ilya Loshchilov and Frank Hutter. Fixing weight decay regularization in adam. CoRR, abs/1711.05101, 2017. URL http://arxiv.org/abs/1711.05101.


Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Diamos, Erich Elsen, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, et al. Mixed precision training. In International Conference on Learning Representations, 2018.


Jeff Rasley, Samyam Rajbhandari, Olatunji Ruwase, and Yuxiong He. Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 3505–3506, 2020.


Zhuyun Dai, Vincent Y Zhao, Ji Ma, Yi Luan, Jianmo Ni, Jing Lu, Anton Bakalov, Kelvin Guu, Keith Hall, and Ming-Wei Chang. Promptagator: Few-shot dense retrieval from 8 examples. In The Eleventh International Conference on Learning Representations, 2023. URL https://openreview.net/forum?id= gmL46YMpu2J.


Aäron van den Oord, Yazhe Li, and Oriol Vinyals. Representation learning with contrastive predictive coding. CoRR, abs/1807.03748, 2018. URL http: //arxiv.org/abs/1807.03748.


Feng Wang and Huaping Liu. Understanding the behaviour of contrastive loss. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2495–2504. IEEE, 2021.


Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, et al. Ms marco: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268, 2016.


Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Matthew Kelcey, Jacob Devlin, Kenton Lee, Kristina N. Toutanova, Llion Jones, Ming-Wei Chang, Andrew Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. Natural questions: a benchmark for question answering research. Transactions of the Association of Computational Linguistics, 2019.


Samuel Bowman, Gabor Angeli, Christopher Potts, and Christopher D Manning. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 632–642, 2015.


Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174, 2016.


Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized BERT pretraining approach. CoRR, abs/1907.11692, 2019b. URL http://arxiv. org/abs/1907.11692.


Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. GLUE: A multi-task benchmark and analysis platform for natural language understanding. CoRR, abs/1804.07461, 2018. URL http://arxiv.org/abs/1804.07461.


Jason Phang, Thibault Févry, and Samuel R. Bowman. Sentence encoders on stilts: Supplementary training on intermediate labeled-data tasks. CoRR, abs/1811.01088, 2018. URL http://arxiv.org/ abs/1811.01088.


Eva Sharma, Chen Li, and Lu Wang. BIGPATENT: A large-scale dataset for abstractive and coherent summarization. CoRR, abs/1906.03741, 2019. URL http://arxiv.org/abs/1906.03741.


Wikimedia Foundation. Wikimedia downloads, 2022. URL https://dumps.wikimedia.org.


David Wadden, Shanchuan Lin, Kyle Lo, Lucy Lu Wang, Madeleine van Zuylen, Arman Cohan, and Hannaneh Hajishirzi. Fact or fiction: Verifying scientific claims. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7534–7550, 2020.