Each week, the Hugging Face team has a science day where one team member presents an awesome NLP paper. We've decided to share this discussion with the community. See planned future discussions below.
Note: These science day discussions are held offline with no physical presentation or discussion to provide. However, some presentation materials do include limited comments from our team or summaries of internal discussions.
- Topic: Overview of recent work on: Indexing and Retrieval for Open Domain Question Answering
- Presenter: Yacine Jernite
- Discussion: Slides
- Paper: Scaling Laws for Neural Language Models
- Authors: Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, Dario Amodei
- Presenter: Teven Le Scao
- Discussion: Google doc paper tutorial
- Paper: Representation Learning with Contrastive Predictive Coding
- Authors: Aaron van den Oord, Yazhe Li, Oriol Vinyals
- Presenter Patrick von Platen
- Discussion: Slides
- Paper: Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
- Authors: R. Thomas McCoy, Ellie Pavlick, Tal Linzen
- Presenter: Victor Sanh
- Discussion: Slides
- Paper: REALM: Retrieval-Augmented Language Model Pre-Training
- Authors: Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, Ming-Wei Chang
- Presenter: Joe Davison
- Discussion: Write-up
- Paper: Adaptively Sparse Transformers
- Authors: Gonçalo M. Correia, Vlad Niculae, André F.T. Martins
- Presenter: Sasha Rush
- Discussion: Colab notebook
- Paper: Compositionality decomposed: how do neural networks generalise?
- Authors: Dieuwke Hupkes, Verna Dankers, Mathijs Mul, Elia Bruni
- Presenter: Thomas Wolf