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

Defending Against Neural Fake News

Rowan ZellersAri HoltzmanHannah RashkinYejin Choi
2019
NeurIPS

Recent progress in natural language generation has raised dual-use concerns. While applications like summarization and translation are positive, the underlying technology also might enable… 

Discovering Neural Wirings

Mitchell WortsmanAli FarhadiMohammad Rastegari
2019
NeurIPS

The success of neural networks has driven a shift in focus from feature engineering to architecture engineering. However, successful networks today are constructed using a small and manually defined… 

What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering

Tushar KhotAshish SabharwalPeter Clark
2019
EMNLP

Multi-hop textual question answering requires combining information from multiple sentences. We focus on a natural setting where, unlike typical reading comprehension, only partial information is… 

Evaluating Question Answering Evaluation

Anthony ChenGabriel StanovskySameer SinghMatt Gardner
2019
EMNLP • MRQA Workshop

As the complexity of question answering (QA) datasets evolve, moving away from restricted formats like span extraction and multiple-choice (MC) to free-form answer generation, it is imperative to… 

On Making Reading Comprehension More Comprehensive

Matt GardnerJonathan BerantHannaneh HajishirziSewon Min
2019
EMNLP • MRQA Workshop

Machine reading comprehension, the task of evaluating a machine’s ability to comprehend a passage of text, has seen a surge in popularity in recent years. There are many datasets that are targeted… 

ORB: An Open Reading Benchmark for Comprehensive Evaluation of Machine Reading Comprehension

Dheeru DuaAnanth GottumukkalaAlon TalmorMatt Gardner
2019
EMNLP • MRQA Workshop

Reading comprehension is one of the crucial tasks for furthering research in natural language understanding. A lot of diverse reading comprehension datasets have recently been introduced to study… 

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…