Share This Author
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
A new question set, text corpus, and baselines assembled to encourage AI research in advanced question answering constitute the AI2 Reasoning Challenge (ARC), which requires far more powerful knowledge and reasoning than previous challenges such as SQuAD or SNLI.
SciTaiL: A Textual Entailment Dataset from Science Question Answering
A new dataset and model for textual entailment, derived from treating multiple-choice question-answering as an entailment problem, is presented, and it is demonstrated that one can improve accuracy on SCITAIL by 5% using a new neural model that exploits linguistic structure.
UnifiedQA: Crossing Format Boundaries With a Single QA System
This work uses the latest advances in language modeling to build a single pre-trained QA model, UNIFIEDQA, that performs well across 19 QA datasets spanning 4 diverse formats, and results in a new state of the art on 10 factoid and commonsense question answering datasets.
Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
A new kind of question answering dataset, OpenBookQA, modeled after open book exams for assessing human understanding of a subject, and oracle experiments designed to circumvent the knowledge retrieval bottleneck demonstrate the value of both the open book and additional facts.
QASC: A Dataset for Question Answering via Sentence Composition
- Tushar Khot, Peter Clark, Michal Guerquin, Peter Alexander Jansen, Ashish Sabharwal
- Computer ScienceAAAI
- 25 October 2019
This work presents a multi-hop reasoning dataset, Question Answering via Sentence Composition (QASC), that requires retrieving facts from a large corpus and composing them to answer a multiple-choice question, and provides annotation for supporting facts as well as their composition.
Gradient-based boosting for statistical relational learning: The relational dependency network case
- Sriraam Natarajan, Tushar Khot, K. Kersting, Bernd Gutmann, J. Shavlik
- Computer ScienceMachine Learning
This work proposes to turn the problem of relational Dependency Networks into a series of relational function-approximation problems using gradient-based boosting, and shows that this boosting method results in efficient learning of RDNs when compared to state-of-the-art statistical relational learning approaches.
Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
This paper describes an alternative approach that operates at three levels of representation and reasoning: information retrieval, corpus statistics, and simple inference over a semi-automatically constructed knowledge base, to achieve substantially improved results.
Question Answering via Integer Programming over Semi-Structured Knowledge
- Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Peter Clark, Oren Etzioni, D. Roth
- Computer ScienceIJCAI
- 20 April 2016
This work proposes a structured inference system for this task, formulated as an Integer Linear Program (ILP), that answers natural language questions using a semi-structured knowledge base derived from text, including questions requiring multi-step inference and a combination of multiple facts.
Learning Markov Logic Networks via Functional Gradient Boosting
- Tushar Khot, Sriraam Natarajan, K. Kersting, J. Shavlik
- Computer ScienceIEEE 11th International Conference on Data Mining
- 1 December 2011
This work proposes to take a different approach, namely to learn both the weights and the structure of the MLN simultaneously, based on functional gradient boosting where the problem of learning MLNs is turned into a series of relational functional approximation problems.
Answering Complex Questions Using Open Information Extraction
This work develops a new inference model for Open IE that can work effectively with multiple short facts, noise, and the relational structure of tuples, and significantly outperforms a state-of-the-art structured solver on complex questions of varying difficulty.