• Publications
  • Influence
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. Expand
Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension
A new dataset and models for comprehending paragraphs about processes, an important genre of text describing a dynamic world, are presented and two new neural models that exploit alternative mechanisms for state prediction are introduced, in particular using LSTM input encoding and span prediction. Expand
Transformers as Soft Reasoners over Language
This work trains transformers to reason (or emulate reasoning) over natural language sentences using synthetically generated data, thus bypassing a formal representation and suggesting a new role for transformers, namely as limited "soft theorem provers" operating over explicit theories in language. Expand
Question Answering via Integer Programming over Semi-Structured Knowledge
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
A Lightweight and High Performance Monolingual Word Aligner
A discriminatively trained monolingual word aligner that uses a Conditional Random Field to globally decode the best alignment with features drawn from source and target sentences to give state-of-the-art result. Expand
Semi-Markov Phrase-Based Monolingual Alignment
We introduce a novel discriminative model for phrase-based monolingual alignment using a semi-Markov CRF. Our model achieves stateof-the-art alignment accuracy on two phrasebased alignment datasetsExpand
Higher-order Lexical Semantic Models for Non-factoid Answer Reranking
This work introduces a higher-order formalism that allows all these lexical semantic models to chain direct evidence to construct indirect associations between question and answer texts, by casting the task as the traversal of graphs that encode direct term associations. Expand
What’s in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams
This work develops an explanation-based analysis of knowledge and inference requirements, which supports a fine-grained characterization of the challenges, and compares a retrieval and an inference solver on 212 questions. Expand
Acquiring and Using World Knowledge Using a Restricted Subset of English
The claim is that this approach hits a “sweet spot” between the former two extremes, being both usable by humans and understandable by machines, and the strengths and weaknesses of restricted natural language as the basis for knowledge representation. Expand
A study of the knowledge base requirements for passing an elementary science test
The analysis suggests that as well as fact extraction from text and statistically driven rule extraction, three other styles of automatic knowledge base construction (AKBC) would be useful: acquiring definitional knowledge, direct 'reading' of rules from texts that state them, and, given a particular representational framework, acquisition of specific instances of those models from text. Expand