40 - On the State of the Art of Evaluation in Neural Language Models, with Gábor Melis
Recent arxiv paper by Gábor Melis, Chris Dyer, and Phil Blunsom. Gábor comes on the podcast to tell us about his work. He performs a thorough comparison between vanilla LSTMs and recurrent highway n...
7 Nov 201729min
39 - Organizing the SemEval task on scientific information extraction, with Isabelle Augenstein
Isabelle Augenstein was the lead organizer of SemEval 2017 task 10, on extracting keyphrases and relations from scientific publications. In this episode we talk about her experience organizing the ta...
1 Nov 201731min
38 - A Corpus of Natural Language for Visual Reasoning, with Alane Suhr
ACL 2017 best resource paper, by Alane Suhr, Mike Lewis, James Yeh, and Yoav Artzi Alane joins us on the podcast to tell us about the dataset, which contains images paired with natural language descr...
30 Okt 201723min
37 - On Statistical Significance, Training Variance, and Why Reporting Score Distributions Matters
In this episode we talk about a couple of recent papers that get at the issue of training variance, and why we should not just take the max from a training distribution when reporting results. Sadly,...
24 Okt 201712min
36 - Attention Is All You Need, with Ashish Vaswani and Jakob Uszkoreit
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 parallelizab...
23 Okt 201741min
35 - Replicability Analysis for Natural Language Processing, with Roi Reichart
TACL 2017 paper by Rotem Dror, Gili Baumer, Marina Bogomolov, and Roi Reichart. Roi comes on to talk to us about how to make better statistical comparisons between two methods when there are multiple...
19 Okt 201731min
34 - Translating Neuralese, with Jacob Andreas
ACL 2017 paper by Jacob Andreas, Anca D. Dragan, and Dan Klein. Jacob comes on to tell us about the paper. The paper focuses on multi-agent dialogue tasks, where two learning systems need to figure ...
17 Okt 201732min
33 - Entity Linking via Joint Encoding of Types, Descriptions, and Context, with Nitish Gupta
EMNLP 2017 paper by Nitish Gupta, Sameer Singh, and Dan Roth. Nitish comes on to talk to us about his paper, which presents a new entity linking model that both unifies prior sources of information i...
16 Okt 201724min
