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

Modeling Naive Psychology of Characters in Simple Commonsense Stories

Hannah RashkinAntoine BosselutMaarten SapKevin Knight and Yejin Choi
2018
ACL

Understanding a narrative requires reading between the lines and reasoning about the unspoken but obvious implications about events and people’s mental states — a capability that is trivial for… 

Simple and Effective Multi-Paragraph Reading Comprehension

Christopher ClarkMatt Gardner
2018
ACL

We consider the problem of adapting neural paragraph-level question answering models to the case where entire documents are given as input. Our proposed solution trains models to produce well… 

Transferring Common-Sense Knowledge for Object Detection

Krishna Kumar SinghSantosh Kumar DivvalaAli Farhadiand Yong Jae Lee
2018
ECCV

We propose the idea of transferring common-sense knowledge from source categories to target categories for scalable object detection. In our setting, the training data for the source categories have… 

Ultra-Fine Entity Typing

Eunsol ChoiOmer LevyYejin Choi and Luke Zettlemoyer
2018
ACL

We introduce a new entity typing task: given a sentence with an entity mention, the goal is to predict a set of free-form phrases (e.g. skyscraper, songwriter, or criminal) that describe appropriate… 

A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications

Dongyeop KangWaleed AmmarBhavana Dalvi MishraRoy Schwartz
2018
NAACL-HLT

Peer reviewing is a central component in the scientific publishing process. We present the first public dataset of scientific peer reviews available for research pur- poses (PeerRead v1), providing… 

Annotation Artifacts in Natural Language Inference Data

Suchin GururanganSwabha SwayamdiptaOmer LevySam Bowman and Noah A. Smith
2018
NAACL

Large-scale datasets for natural language inference are created by presenting crowd workers with a sentence (premise), and asking them to generate three new sentences (hypotheses) that it entails,… 

Content-Based Citation Recommendation

Chandra BhagavatulaSergey FeldmanRussell PowerWaleed Ammar
2018
NAACL-HLT

We present a content-based method for recommending citations in an academic paper draft. We embed a given query document into a vector space, then use its nearest neighbors as candidates, and rerank… 

Deep Communicating Agents For Abstractive Summarization

Asli CelikyilmazAntoine BosselutXiaodong He and Yejin Choi
2018
NAACL

We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. With deep communicating agents, the… 

Deep Contextualized Word Representations

Matthew E. PetersMark NeumannMohit IyyerLuke Zettlemoyer
2018
NAACL

We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across… 

Discourse-Aware Neural Rewards For Coherent Text Generation

Antoine BosselutAsli CelikyilmazXiaodong HePo-Sen Huang and Yejin Choi
2018
NAACL

In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to…