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

Declarative Question Answering over Knowledge Bases containing Natural Language Text with Answer Set Programming

Arindam MitraPeter ClarkOyvind TafjordChitta Baral
2019
AAAI

While in recent years machine learning (ML) based approaches have been the popular approach in developing end-to-end question answering systems, such systems often struggle when additional knowledge… 

QASC: A Dataset for Question Answering via Sentence Composition

Tushar KhotPeter ClarkMichal GuerquinAshish Sabharwal
2019
AAAI

Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition (QASC),… 

QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships

Oyvind TafjordPeter ClarkMatt GardnerAshish Sabharwal
2019
AAAI

Many natural language questions require recognizing and reasoning with qualitative relationships (e.g., in science, economics, and medicine), but are challenging to answer with corpus-based methods.… 

On the Capabilities and Limitations of Reasoning for Natural Language Understanding

Daniel KhashabiErfan Sadeqi AzerTushar KhotDan Roth
2019
arXiv

Recent systems for natural language understanding are strong at overcoming linguistic variability for lookup style reasoning. Yet, their accuracy drops dramatically as the number of reasoning steps… 

Expanding Holographic Embeddings for Knowledge Completion

Yexiang XueYang YuanZhitian XuAshish Sabharwal
2018
NeurIPS

Neural models operating over structured spaces such as knowledge graphs require a continuous embedding of the discrete elements of this space (such as entities) as well as the relationships between… 

Bridging Knowledge Gaps in Neural Entailment via Symbolic Models

Dongyeop KangTushar KhotAshish Sabharwal and Peter Clark
2018
EMNLP

Most textual entailment models focus on lexical gaps between the premise text and the hypothesis, but rarely on knowledge gaps. We focus on filling these knowledge gaps in the Science Entailment… 

Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Todor MihaylovPeter ClarkTushar KhotAshish Sabharwal
2018
EMNLP

We present a new kind of question answering dataset, OpenBookQA, modeled after open book exams for assessing human understanding of a subject. The open book that comes with our questions is a set of… 

Reasoning about Actions and State Changes by Injecting Commonsense Knowledge

Niket TandonBhavana Dalvi MishraJoel GrusPeter Clark
2018
EMNLP

Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can… 

Adaptive Stratified Sampling for Precision-Recall Estimation

Ashish SabharwalYexiang Xue
2018
UAI

We propose a new algorithm for computing a constant-factor approximation of precision-recall (PR) curves for massive noisy datasets produced by generative models. Assessing validity of items in such… 

Adversarial Training for Textual Entailment with Knowledge-Guided Examples

Tushar KhotAshish Sabharwal and Dongyeop Kang
2018
ACL

We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided…