• Publications
  • Influence
SciTaiL: A Textual Entailment Dataset from Science Question Answering
TLDR
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. Expand
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
TLDR
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. Expand
UnifiedQA: Crossing Format Boundaries With a Single QA System
TLDR
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. Expand
Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
TLDR
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. Expand
Gradient-based boosting for statistical relational learning: The relational dependency network case
TLDR
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. Expand
QASC: A Dataset for Question Answering via Sentence Composition
TLDR
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 presents a two-step approach to mitigate the retrieval challenges. Expand
Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
TLDR
This paper evaluates the methods on six years of unseen, unedited exam questions from the NY Regents Science Exam, and shows that the overall system's score is 71.3%, an improvement of 23.8% (absolute) over the MLN-based method described in previous work. Expand
Question Answering via Integer Programming over Semi-Structured Knowledge
TLDR
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. Expand
Learning Markov Logic Networks via Functional Gradient Boosting
TLDR
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. Expand
Question Answering as Global Reasoning Over Semantic Abstractions
TLDR
This work presents the first system that reasons over a wide range of semantic abstractions of the text, which are derived using off-the-shelf, general-purpose, pre-trained natural language modules such as semantic role labelers, coreference resolvers, and dependency parsers. Expand
...
1
2
3
4
5
...