Awesome Podcast

In this episode we briefly say what we're up to with the podcast.  No technical content, just a description of what each episode will look like, and why we're doing this.

00 - Intro to the podcast

https://www.semanticscholar.org/paper/A-Comparative-Study-of-Word-Embeddings-for-Reading-Dhingra-Liu/3ec37205c9201fc891ab51da200e361fdc34bfb3

01 - A Comparative Study of Word Embeddings for Reading Comprehension

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/FastQA-A-Simple-and-Efficient-Neural-Architecture-Weissenborn-Wiese/7c1576b96a1e246d77b30f7b80cec63be96fa698

03 - FastQA: A Simple and Efficient Neural Architecture for Question Answering

An interview with Chris Dyer.

https://www.semanticscholar.org/paper/Recurrent-Neural-Network-Grammars-Dyer-Kuncoro/1594d954abc650bce2db445c52a76e49655efb0c

04 - Recurrent Neural Network Grammars, with Chris Dyer

https://www.semanticscholar.org/paper/Design-Challenges-for-Entity-Linking-Ling-Singh/aa2a7ac7bfa9a0201d4faddd4e7bb26299a5e0be

06 - Design Challenges for Entity Linking

https://www.semanticscholar.org/paper/Learning-to-Generate-Reviews-and-Discovering-Senti-Radford-Jozefowicz/664ec878de4b7170712baae4a7821fc2602bba25

https://blog.openai.com/unsupervised-sentiment-neuron/

09 - Learning to Generate Reviews and Discovering Sentiment

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

https://www.semanticscholar.org/paper/Generalizing-to-Unseen-Entities-and-Entity-Pairs-w-Verga-Neelakantan/7dd8b958632b07e41979337c71d847a3f39df456

18 - Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema

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, our current focus on performance in leaderboards only exacerbates these issues, and (in my opinion) encourages bad science.

Papers:
https://www.semanticscholar.org/paper/Reporting-Score-Distributions-Makes-a-Difference-P-Reimers-Gurevych/0eae432f7edacb262f3434ecdb2af707b5b06481
https://www.semanticscholar.org/paper/Deep-Reinforcement-Learning-that-Matters-Henderson-Islam/90dad036ab47d683080c6be63b00415492b48506

37 - On Statistical Significance, Training Variance, and Why Reporting Score Distributions Matters

EMNLP 2018 paper by Dirk Hovy and Tommaso Fornaciari. https://www.semanticscholar.org/paper/Improving-Author-Attribute-Prediction-by-Linguistic-Hovy-Fornaciari/71aad8919c864f73108aafd8e926d44e9df51615

In this episode, Dirk Hovy talks about natural language as social phenomenon which can provide insights about those who generate it. For example, this paper uses retrofitted embeddings to improve on two tasks: predicting the gender and age group of a person based on their online reviews. In this approach, authors embeddings are first generated using Doc2Vec, then retrofitted such that authors with similar attributes are closer in the vector space. In order to estimate the retrofitted vectors for authors with unknown attributes, a linear transformation is learned which maps Doc2Vec vectors to the retrofitted vectors. Dirk also used a similar approach to encode geographic information to model regional linguistic variations, in another EMNLP 2018 paper with Christoph Purschke titled “Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting” [link: https://www.semanticscholar.org/paper/Capturing-Regional-Variation-with-Distributed-Place-Hovy-Purschke/6d9babd835d0cdaaf175f098bb4fd61fd75b1be0].

76 - Increasing In-Class Similarity by Retrofitting Embeddings with Demographics, with Dirk Hovy

Originally used to entice fierce competitions in arcade games, leaderboards recently made their way into NLP research circles. Leaderboards could help mitigate some of the problems in how researchers run experiments and share results (e.g., accidentally overfitting models on a test set), but they also introduce new problems (e.g., breaking author anonymity in peer reviewing). In this episode, Siva Reddy joins us to talk about the good, the bad, and the ugly of using leaderboards in science. We also discuss potential solutions to address some of the outstanding problems with existing leaderboard frameworks.

Software platforms for leaderboards: 
http://codalab.org/ 
https://leaderboard.allenai.org/

80 - Leaderboards and Science, with Siva Reddy

In this episode, we invite Sebastian Riedel to talk about knowledge base construction (KBC). Why is it an important research area? What are the tradeoffs between using an open vs. closed schema? What are popular methods currently used, and what challenges prevent the adoption of KBC methods? We also briefly discuss the AKBC workshop and its graduation into a conference in 2019.

Sebastian Riedel's homepage: http://www.riedelcastro.org/
AKBC conference: http://www.akbc.ws/2019/

83 - Knowledge Base Construction, with Sebastian Riedel

In this episode, we invite Jonathan Berant to talk about executable semantic parsing. We discuss what executable semantic parsing is and how it differs from related tasks such as semantic dependency parsing and abstract meaning representation (AMR) parsing. We talk about the main components of a semantic parser, how the formal language affects design choices in the parser, and end with a discussion of some exciting open problems in this space.

Jonathan Berant's homepage: http://www.cs.tau.ac.il/~joberant/

91 - (Executable) Semantic Parsing, with Jonathan Berant

In this episode, we chat with Luke Zettlemoyer about Question Answering as a format for crowdsourcing annotations of various semantic phenomena in text. We start by talking about QA-SRL and QAMR, two datasets that use QA pairs to annotate predicate-argument relations at the sentence level. Luke describes how this annotation scheme makes it possible to obtain annotations from non-experts, and discusses the tradeoffs involved in choosing this scheme. Then we talk about the challenges involved in using QA-based annotations for more complex phenomena like coreference. Finally, we briefly discuss the value of crowd-labeled datasets given the recent developments in pretraining large language models. Luke is an associate professor at the University of Washington and a Research Scientist at Facebook AI Research.

96 - Question Answering as an Annotation Format, with Luke Zettlemoyer

**The podcast is currently on hiatus. For more active NLP content, check out the Holistic Intelligence Podcast linked below.**

Welcome to the NLP highlights podcast, where we invite researchers to talk about their work in various areas in natural language processing. All views expressed belong to the hosts/guests, and do not represent their employers.

37 - On Statistical Significance, Training Variance, and Why Reporting Score Distributions Matters

NLP Highlights