Tushar Khot

Publications
Influence

SciTaiL: A Textual Entailment Dataset from Science Question Answering

Tushar Khot, A. Sabharwal, Peter Clark
Computer Science
AAAI
7 February 2018

We present a new dataset and model for textual entailment, derived from treating multiple-choice question-answering as an entailment problem. SCITAIL is the first entailment set that is created… Expand

Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Peter Clark, Isaac Cowhey, +4 authors Oyvind Tafjord
Computer Science
ArXiv
14 March 2018

We present a new question set, text corpus, and baselines assembled to encourage AI research in advanced question answering. Together, these constitute the AI2 Reasoning Challenge (ARC), which… Expand

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

Todor Mihaylov, Peter Clark, Tushar Khot, A. Sabharwal
Computer Science
EMNLP
8 September 2018

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… Expand

Gradient-based boosting for statistical relational learning: The relational dependency network case

Sriraam Natarajan, Tushar Khot, K. Kersting, B. Gutmann, J. Shavlik
Mathematics, Computer Science
Machine Learning
2011

Dependency networks approximate a joint probability distribution over multiple random variables as a product of conditional distributions. Relational Dependency Networks (RDNs) are graphical models… Expand

QASC: A Dataset for Question Answering via Sentence Composition

Tushar Khot, Peter Clark, Michal Guerquin, P. Jansen, A. Sabharwal
Computer Science
AAAI
25 October 2019

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), that… Expand

Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions

Peter Clark, Oren Etzioni, +4 authors Daniel Khashabi
Computer Science
AAAI
12 February 2016

What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background… Expand

Question Answering via Integer Programming over Semi-Structured Knowledge

Daniel Khashabi, Tushar Khot, A. Sabharwal, P. Clark, Oren Etzioni, D. Roth
Computer Science
IJCAI
20 April 2016

Answering science questions posed in natural language is an important AI challenge. Answering such questions often requires non-trivial inference and knowledge that goes beyond factoid retrieval.… Expand

Learning Markov Logic Networks via Functional Gradient Boosting

Tushar Khot, Sriraam Natarajan, K. Kersting, J. Shavlik
Computer Science
IEEE 11th International Conference on Data Mining
11 December 2011

Recent years have seen a surge of interest in Statistical Relational Learning (SRL) models that combine logic with probabilities. One prominent example is Markov Logic Networks (MLNs). While MLNs are… Expand

How creative is your writing? A linguistic creativity measure from computer science and cognitive psychology perspectives

Xiaojin Zhu, Z. Xu, Tushar Khot
Psychology
4 June 2009

We demonstrate that subjective creativity in sentence-writing can in part be predicted using computable quantities studied in Computer Science and Cognitive Psychology. We introduce a task in which a… Expand

Markov Logic Networks for Natural Language Question Answering

Tushar Khot, Niranjan Balasubramanian, Eric Gribkoff, A. Sabharwal, P. Clark, Oren Etzioni
Computer Science
ArXiv
10 July 2015

Our goal is to answer elementary-level science questions using knowledge extracted automatically from science textbooks, expressed in a subset of first-order logic. Given the incomplete and noisy… Expand

Recommended Authors