• Publications
  • Influence
AllenNLP: A Deep Semantic Natural Language Processing Platform
TLDR
This paper describes AllenNLP, a platform for research on deep learning methods in natural language understanding. Expand
  • 508
  • 76
  • PDF
DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
TLDR
We introduce a new reading comprehension benchmark, DROP, which requires Discrete Reasoning Over the content of Paragraphs. Expand
  • 141
  • 30
  • PDF
Neural Semantic Parsing with Type Constraints for Semi-Structured Tables
TLDR
We present a new semantic parsing model for answering compositional questions on semi-structured Wikipedia tables. Expand
  • 121
  • 16
  • PDF
Subgroup Detection in Ideological Discussions
TLDR
The rapid and continuous growth of social networking sites has led to the emergence of many communities of communicating groups. Expand
  • 61
  • 11
  • PDF
Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning
TLDR
We present a new crowdsourced dataset containing more than 24K span-selection questions that require resolving coreference among entities in over 4.7K English paragraphs from Wikipedia. Expand
  • 36
  • 7
  • PDF
Tharwa: A Large Scale Dialectal Arabic - Standard Arabic - English Lexicon
TLDR
We introduce an electronic three-way lexicon, Tharwa, comprising Dialectal Arabic, Modern Standard Arabic and English correspondents. Expand
  • 35
  • 2
  • PDF
Iterative Search for Weakly Supervised Semantic Parsing
TLDR
We propose a novel iterative training algorithm that alternates between searching for consistent logical forms and maximizing the marginal likelihood of the retrieved ones. Expand
  • 10
  • 2
  • PDF
Evaluating NLP Models via Contrast Sets
TLDR
We propose a new annotation paradigm for NLP that helps to close systematic gaps in the test data. Expand
  • 42
  • 1
  • PDF
Ontology-Aware Token Embeddings for Prepositional Phrase Attachment
TLDR
We use the new, context-sensitive embeddings in a model for predicting prepositional phrase(PP) attachments and jointly learn the concept embedDings and model parameters. Expand
  • 25
  • 1
  • PDF
Automated detection of discourse segment and experimental types from the text of cancer pathway results sections
TLDR
Automated machine-reading biocuration systems typically use sentence-by-sentence information extraction to construct meaning representations for use by curators. Expand
  • 12
  • 1
  • PDF