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

Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text

Bhavana Dalvi MishraNiket TandonAntoine BosselutPeter Clark
2019
EMNLP

Our goal is to better comprehend procedural text, e.g., a paragraph about photosynthesis, by not only predicting what happens, but why some actions need to happen before others. Our approach builds… 

“Going on a vacation” takes longer than “Going for a walk”: A Study of Temporal Commonsense Understanding

Ben ZhouDaniel KhashabiQiang NingDan Roth
2019
EMNLP

Understanding time is crucial for understanding events expressed in natural language. Because people rarely say the obvious, it is often necessary to have commonsense knowledge about various… 

Pretrained Language Models for Sequential Sentence Classification

Arman CohanIz BeltagyDaniel KingDaniel S. Weld
2019
EMNLP

As a step toward better document-level understanding, we explore classification of a sequence of sentences into their corresponding categories, a task that requires understanding sentences in… 

QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions

Oyvind TafjordMatt GardnerKevin LinPeter Clark
2019
EMNLP

We introduce the first open-domain dataset, called QuaRTz, for reasoning about textual qualitative relationships. QuaRTz contains general qualitative statements, e.g., "A sunscreen with a higher SPF… 

WIQA: A dataset for "What if..." reasoning over procedural text

Niket TandonBhavana Dalvi MishraKeisuke SakaguchiPeter Clark
2019
EMNLP

We introduce WIQA, the first large-scale dataset of "What if..." questions over procedural text. WIQA contains three parts: a collection of paragraphs each describing a process, e.g., beach erosion;… 

Exploiting Explicit Paths for Multi-hop Reading Comprehension

Souvik KunduTushar KhotAshish SabharwalPeter Clark
2019
ACL

We propose a novel, path-based reasoning approach for the multi-hop reading comprehension task where a system needs to combine facts from multiple passages to answer a question. Although inspired by… 

Be Consistent! Improving Procedural Text Comprehension using Label Consistency

Xinya DuBhavana Dalvi MishraNiket TandonClaire Cardie
2019
NAACL-HLT

Our goal is procedural text comprehension, namely tracking how the properties of entities (e.g., their location) change with time given a procedural text (e.g., a paragraph about photosynthesis, a… 

Repurposing Entailment for Multi-Hop Question Answering Tasks

Harsh TrivediHeeyoung KwonTushar KhotNiranjan Balasubramanian
2019
NAACL

Question Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning… 

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),…