https://www.semanticscholar.org/paper/Bidirectional-Attention-Flow-for-Machine-Seo-Kembhavi/007ab5528b3bd310a80d553cccad4b78dc496b02

02 - Bidirectional Attention Flow for Machine Comprehension

https://www.semanticscholar.org/paper/Question-Answering-from-Unstructured-Text-by-Retri-Watanabe-Dhingra/89d06c2996f379c602e64b4243f026cd164400d7

13 - Question Answering from Unstructured Text by Retrieval and Comprehension

ACL 2017 paper by Abigail See, Peter Liu, and Chris Manning.

Matt presents the paper, describing the task (summarization on CNN/Daily Mail), the model (the standard copy + generate model that people are using these days, plus a nice coverage loss term), and the results (can't beat the extractive baseline, but coming close).  It's a nice paper - very well written, interesting discussion section.

https://www.semanticscholar.org/paper/Get-To-The-Point-Summarization-with-Pointer-Genera-See-Liu/13db673d09f546698e0bfb6687beeb5345f81ad9

Abigail also has a very nice blog post where she describes her work in a less formal tone than the paper: http://www.abigailsee.com/2017/04/16/taming-rnns-for-better-summarization.html

23 - Get To The Point: Summarization with Pointer-Generator Networks

NIPS 2017 paper.

We dig into the details of the Transformer, from the "attention is all you need" paper.  Ashish and Jakob give us some motivation for replacing RNNs and CNNs with a more parallelizable self-attention mechanism, they describe how this mechanism works, and then we spend the bulk of the episode trying to get their intuitions for _why_ it works.  We discuss the positional encoding mechanism, multi-headed attention, trying to use these ideas to replace encoders in other models, and what the self-attention actually learns.  Turns out that the lower layers learn something like n-grams (similar to CNNs), and the higher layers learn more semantic-y things, like coreference.

https://www.semanticscholar.org/paper/Attention-Is-All-You-Need-Vaswani-Shazeer/0737da0767d77606169cbf4187b83e1ab62f6077

Minor correction: Talking about complexity equations without the paper in front of you can be tricky, and Ashish and Jakob may have gotten some of the details slightly wrong when we were discussing computational complexity.  The high-level point is that self-attention is cheaper than RNNs when the hidden dimension is higher than the sequence length.  See the paper for more details.

36 - Attention Is All You Need, with Ashish Vaswani and Jakob Uszkoreit

ACL 2017 paper, by Paramita Mirza, Simon Razniewski, Fariz Darari, and Gerhard Weikum.

There's not a whole lot of work on numbers in NLP, and getting good information out of numbers expressed in text can be challenging.  In this episode, Paramita comes on to tell us about her efforts to use distant supervision to learn models that extract relation cardinalities from text.  That is, given an entity and a relation in a knowledge base, like "Barack Obama" and "has child", the goal is to extract _how many_ related entities there are (in this case, two).  There are a lot of challenges in getting this to work well, and Paramita describes some of those, and how she solved them.

https://www.semanticscholar.org/paper/Cardinal-Virtues-Extracting-Relation-Cardinalities-Mirza-Razniewski/01afba9f40e0df06446b9cd3d5ea8725c4ba1342

50 - Cardinal Virtues: Extracting Relation Cardinalities from Text, with Paramita Mirza

NAACL 2018 paper, by Matt Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Chris Clark, Kenton Lee, and Luke Zettlemoyer.

In this episode, AI2's own Matt Peters comes on the show to talk about his recent work on ELMo embeddings, what some have called "the next word2vec".  Matt has shown very convincingly that using a pre-trained bidirectional language model to get contextualized word representations performs substantially better than using static word vectors.  He comes on the show to give us some more intuition about how and why this works, and to talk about some of the other things he tried and what's coming next.

https://www.semanticscholar.org/paper/Deep-contextualized-word-representations-Peters-Neumann/4b17597b856c087f109381ce77d60d9017cb6f9a

NLP Highlights

56 - Deep contextualized word representations, with Matthew Peters

Upcoming JAIR paper by Sebastian Ruder, Ivan Vulić, and Anders Søgaard.

Sebastian comes on to tell us about his survey.  He creates a typology of cross-lingual word embedding methods, and we discuss why you might use cross-lingual embeddings (low-resource languages in particular), what information they capture (semantics? syntax? both?), how the methods work (lots of different ways), and how to evaluate the embeddings (best when you have an extrinsic task to evaluate on).

https://www.semanticscholar.org/paper/A-survey-of-cross-lingual-embedding-models-Ruder/3dbd28c63a7807280c9531735c715d4598024166

Episode 57_Sebastian Ruder

57 - A Survey Of Cross-lingual Word Embedding Models, with Sebastian Ruder

Blog post by Alex Irpan titled "Deep Reinforcement Learning Doesn't Work Yet"
https://www.alexirpan.com/2018/02/14/rl-hard.html

In this episode, Alex Irpan talks about limitations of current deep reinforcement learning methods and why we have a long way to go before they go mainstream. We discuss sample inefficiency, instability, the difficulty to design reward functions and overfitting to the environment. Alex concludes with a list of recommendations he found useful when training models with deep reinforcement learning.

74 - Deep Reinforcement Learning Doesn't Work Yet, with Alex Irpan

In this episode we talked with Victor Sanh and Thomas Wolf from HuggingFace about model distillation, and DistilBERT as one example of distillation. The idea behind model distillation is compressing a large model by building a smaller model, with much fewer parameters, that approximates the output distribution of the original model, typically for increased efficiency. We discussed how model distillation was typically done previously, and then focused on the specifics of DistilBERT, including training objective, empirical results, ablations etc. We finally discussed what kinds of information you might lose when doing model distillation.

NLP

Arindam Paul