Neural net attention mechanisms

On brilliance through selective ignorance


What’s that now? Long story, but see transformer or Sparse Transformer etc for particularly developed examples and explanations of this sub-field. The best illustraede blog post is Jay Alammar’s Illustrated Transformer.

These networks are absolutely massive (heh) in natural language processing right now.

For the transformer network at least there seems to be an unexpectedly computationally efficient trade-off where you can go faster by training a bigger network.

A good paper read is Yannic Kilcher’s.

HuggingFace distributes and documents and implements a lot of Transformer/attention NLP models and seem to be the most active neural NLP project. Certainly too active to explain what they are up to in between pumping out all the code.

The library currently contains PyTorch and Tensorflow implementations, pre-trained model weights, usage scripts and conversion utilities for the following models:

  1. BERT (from Google) released with the paper BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova.
  2. GPT (from OpenAI) released with the paper Improving Language Understanding by Generative Pre-Training by Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever.
  3. GPT-2 (from OpenAI) released with the paper Language Models are Unsupervised Multitask Learners by Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever.
  4. Transformer-XL (from Google/CMU) released with the paper Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context by Zihang Dai, Zhilin Yang, Yiming Yang, Jaime Carbonell, Quoc V. Le, and Ruslan Salakhutdinov.
  5. XLNet (from Google/CMU) released with the paper ​XLNet: Generalized Autoregressive Pretraining for Language Understanding by Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, and Quoc V. Le.
  6. XLM (from Facebook) released together with the paper Cross-lingual Language Model Pretraining by Guillaume Lample and Alexis Conneau.
  7. RoBERTa (from Facebook), released together with the paper a Robustly Optimized BERT Pretraining Approach by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov.
  8. DistilBERT (from HuggingFace) released together with the paper DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter by Victor Sanh, Lysandre Debut, and Thomas Wolf. The same method has been applied to compress GPT2 into DistilGPT2.
  9. [very long list excised]

Bahdanau, Dzmitry, Kyunghyun Cho, and Yoshua Bengio. 2015. “Neural Machine Translation by Jointly Learning to Align and Translate.” In. http://arxiv.org/abs/1409.0473.

Brown, Tom B., Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, et al. 2020. “Language Models Are Few-Shot Learners.” June 1, 2020. http://arxiv.org/abs/2005.14165.

Celikyilmaz, Asli, Li Deng, Lihong Li, and Chong Wang. 2017. “Scaffolding Networks for Teaching and Learning to Comprehend.” February 28, 2017. http://arxiv.org/abs/1702.08653.

Choy, Christopher B, JunYoung Gwak, Silvio Savarese, and Manmohan Chandraker. 2016. “Universal Correspondence Network.” In Advances in Neural Information Processing Systems 29, edited by D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett, 2406–14. Curran Associates, Inc. http://papers.nips.cc/paper/6487-universal-correspondence-network.pdf.

Freeman, Alexandra L J. 2019. “How to Communicate Evidence to Patients.” Drug and Therapeutics Bulletin 57 (8): 119–24. https://doi.org/10.1136/dtb.2019.000008.

Huang, Cheng-Zhi Anna, Ashish Vaswani, Jakob Uszkoreit, Noam Shazeer, Ian Simon, Curtis Hawthorne, Andrew M. Dai, Matthew D. Hoffman, Monica Dinculescu, and Douglas Eck. 2018. “Music Transformer,” September. https://arxiv.org/abs/1809.04281v3.

Huang, Cheng-Zhi Anna, Ashish Vaswani, Jakob Uszkoreit, Ian Simon, Curtis Hawthorne, Noam Shazeer, Andrew M. Dai, Matthew D. Hoffman, Monica Dinculescu, and Douglas Eck. 2018. “Music Transformer: Generating Music with Long-Term Structure,” September. https://openreview.net/forum?id=rJe4ShAcF7.

Katharopoulos, Angelos, Apoorv Vyas, Nikolaos Pappas, and François Fleuret. 2020. “Transformers Are RNNs: Fast Autoregressive Transformers with Linear Attention.” August 31, 2020. http://arxiv.org/abs/2006.16236.

Li, Zhuohan, Eric Wallace, Sheng Shen, Kevin Lin, Kurt Keutzer, Dan Klein, and Joseph E. Gonzalez. 2020. “Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers.” February 26, 2020. http://arxiv.org/abs/2002.11794.

Radford, Alec, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. “Language Models Are Unsupervised Multitask Learners,” 24.

Ramsauer, Hubert, Bernhard Schäfl, Johannes Lehner, Philipp Seidl, Michael Widrich, Lukas Gruber, Markus Holzleitner, et al. 2020. “Hopfield Networks Is All You Need.” July 16, 2020. http://arxiv.org/abs/2008.02217.

Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. “Attention Is All You Need.” June 12, 2017. http://arxiv.org/abs/1706.03762.