• Publications
  • Influence
Scaling Semantic Parsers with On-the-Fly Ontology Matching
We consider the challenge of learning semantic parsers that scale to large, open-domain problems, such as question answering with Freebase. In such settings, the sentences cover a wide variety ofExpand
  • 275
  • 37
  • PDF
Natural Questions: A Benchmark for Question Answering Research
We present the Natural Questions corpus, a question answering data set. Questions consist of real anonymized, aggregated queries issued to the Google search engine. An annotator is presented with aExpand
  • 221
  • 33
  • PDF
Inducing Probabilistic CCG Grammars from Logical Form with Higher-Order Unification
This paper addresses the problem of learning to map sentences to logical form, given training data consisting of natural language sentences paired with logical representations of their meaning.Expand
  • 289
  • 32
  • PDF
Association for Computational Linguistics: Human Language Technologies
  • 325
  • 22
BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
In this paper we study yes/no questions that are naturally occurring --- meaning that they are generated in unprompted and unconstrained settings. We build a reading comprehension dataset, BoolQ, ofExpand
  • 51
  • 19
  • PDF
Lexical Generalization in CCG Grammar Induction for Semantic Parsing
We consider the problem of learning factored probabilistic CCG grammars for semantic parsing from data containing sentences paired with logical-form meaning representations. Traditional CCG lexiconsExpand
  • 192
  • 18
  • PDF
Learning Recurrent Span Representations for Extractive Question Answering
The reading comprehension task, that asks questions about a given evidence document, is a central problem in natural language understanding. Recent formulations of this task have typically focused onExpand
  • 111
  • 18
  • PDF
Matching the Blanks: Distributional Similarity for Relation Learning
General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that representExpand
  • 74
  • 16
  • PDF
Early stroke treatment associated with better outcome: the ninds rt-pa stroke study
Background The National Institute of Neurological Disorders and Stroke (NINDS) rt-PA Stroke Study showed a similar percentage of intracranial hemorrhage and good outcome in patients 3 months afterExpand
  • 473
  • 10
Transforming Dependency Structures to Logical Forms for Semantic Parsing
The strongly typed syntax of grammar formalisms such as CCG, TAG, LFG and HPSG offers a synchronous framework for deriving syntactic structures and semantic logical forms. In contrast—partly due toExpand
  • 120
  • 9
  • PDF