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

End-to-end Neural Coreference Resolution

Kenton LeeLuheng HeMike Lewisand Luke Zettlemoyer
2017
EMNLP

We introduce the first end-to-end coreference resolution model and show that it significantly outperforms all previous work without using a syntactic parser or handengineered mention detector. The… 

Ontology Aware Token Embeddings for Prepositional Phrase Attachment

Pradeep DasigiWaleed AmmarChris Dyerand Eduard Hovy
2017
ACL

Type-level word embeddings use the same set of parameters to represent all instances of a word regardless of its context, ignoring the inherent lexical ambiguity in language. Instead, we embed… 

The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task

Roy SchwartzMaarten SapIoannis KonstasNoah A. Smith
2017
CoNLL

A writer’s style depends not just on personal traits but also on her intent and mental state. In this paper, we show how variants of the same writing task can lead to measurable differences in… 

Automatic Selection of Context Configurations for Improved Class-Specific Word Representations

Ivan VulicRoy SchwartzAri Rappoportand Anna Korhonen
2017
CoNLL

This paper is concerned with identifying contexts useful for training word representation models for different word classes such as adjectives (A), verbs (V), and nouns (N). We introduce a simple… 

Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification

Rebecca SharpMihai SurdeanuPeter Jansenand Michael Hammond
2017
CoNLL

For many applications of question answering (QA), being able to explain why a given model chose an answer is critical. However, the lack of labeled data for answer justifications makes learning this… 

Learning What is Essential in Questions

Daniel KhashabiTushar KhotAshish Sabharwaland Dan Roth
2017
CoNLL

Question answering (QA) systems are easily distracted by irrelevant or redundant words in questions, especially when faced with long or multi-sentence questions in difficult domains. This paper… 

Crowdsourcing Multiple Choice Science Questions

Johannes WelblNelson F. Liuand Matt Gardner
2017
EMNLP • Workshop on Noisy User-generated Text

We present a novel method for obtaining high-quality, domain-targeted multiple choice questions from crowd workers. Generating these questions can be difficult without trading away originality,… 

QSAnglyzer: Visual Analytics for Prismatic Analysis of Question Answering System Evaluations

Nan-Chen Chen and Been Kim
2017
VAST

Developing sophisticated artificial intelligence (AI) systems requires AI researchers to experiment with different designs and analyze results from evaluations (we refer this task as evaluation… 

AI zooms in on highly influential citations

Oren Etzioni
2017
Nature

The number of times a paper is cited is a poor proxy for its impact (see P. Stephan et al. Nature 544, 411–412; 2017). I suggest relying instead on a new metric that uses artificial intelligence… 

End-to-End Neural Ad-hoc Ranking with Kernel Pooling

Chenyan XiongZhuyun DaiJamie Callanand Russell Power
2017
SIGIR

This paper proposes K-NRM, a kernel based neural model for document ranking. Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word…