Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

Reasoning Over Paragraph Effects in Situations

Kevin LinOyvind TafjordPeter ClarkMatt Gardner
2019
EMNLP • MRQA Workshop

A key component of successfully reading a passage of text is the ability to apply knowledge gained from the passage to a new situation. In order to facilitate progress on this kind of reading, we… 

A Discrete Hard EM Approach for Weakly Supervised Question Answering

Sewon MinDanqi ChenHannaneh HajishirziLuke Zettlemoyer
2019
EMNLP

Many question answering (QA) tasks only provide weak supervision for how the answer should be computed. For example, TriviaQA answers are entities that can be mentioned multiple times in supporting… 

AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models

Eric WallaceJens TuylsJunlin WangSameer Singh
2019
EMNLP

Neural NLP models are increasingly accurate but are imperfect and opaque---they break in counterintuitive ways and leave end users puzzled at their behavior. Model interpretation methods ameliorate… 

BERT for Coreference Resolution: Baselines and Analysis

Mandar JoshiOmer LevyDaniel S. WeldLuke Zettlemoyer
2019
EMNLP

We apply BERT to coreference resolution, achieving strong improvements on the OntoNotes (+3.9 F1) and GAP (+11.5 F1) benchmarks. A qualitative analysis of model predictions indicates that, compared… 

BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle

Peter WestAri HoltzmanJan BuysYejin Choi
2019
EMNLP

The principle of the Information Bottleneck (Tishby et al. 1999) is to produce a summary of information X optimized to predict some other relevant information Y. In this paper, we propose a novel… 

COSMOS QA: Machine Reading Comprehension with Contextual Commonsense Reasoning

Lifu HuangRonan Le BrasChandra BhagavatulaYejin Choi
2019
EMNLP

Understanding narratives requires reading between the lines, which in turn, requires interpreting the likely causes and effects of events, even when they are not mentioned explicitly. In this paper,… 

Counterfactual Story Reasoning and Generation

Lianhui QinAntoine BosselutAri HoltzmanYejin Choi
2019
EMNLP

Counterfactual reasoning requires predicting how alternative events, contrary to what actually happened, might have resulted in different outcomes. Despite being considered a necessary component of… 

Do NLP Models Know Numbers? Probing Numeracy in Embeddings

Eric WallaceYizhong WangSujian LiMatt Gardner
2019
EMNLP

The ability to understand and work with numbers (numeracy) is critical for many complex reasoning tasks. Currently, most NLP models treat numbers in text in the same way as other tokens---they embed… 

Don't paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsing

Jonathan HerzigJonathan Berant
2019
EMNLP

A major hurdle on the road to conversational interfaces is the difficulty in collecting data that maps language utterances to logical forms. One prominent approach for data collection has been to… 

Efficient Navigation with Language Pre-training and Stochastic Sampling

Xiujun LiChunyuan LiQiaolin XiaYejin Choi
2019
EMNLP

Core to the vision-and-language navigation (VLN) challenge is building robust instruction representations and action decoding schemes, which can generalize well to previously unseen instructions and…