• Publications
  • Influence
Semi-supervised sequence tagging with bidirectional language models
We propose a general semi-supervised approach for adding pre-trained context embeddings from bidirectional language models to NLP systems and apply it to sequence labeling tasks. Expand
  • 308
  • 33
ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning
We present ATOMIC, an atlas of everyday commonsense reasoning, organized through 877k textual descriptions of inferential knowledge about events described in natural language and associated with typed if-then relations. Expand
  • 95
  • 22
TabEL: Entity Linking in Web Tables
We present TabEL, a new EL system that performs the Entity Linking task on phrases in cells of Web tables. Expand
  • 72
  • 15
Methods for exploring and mining tables on Wikipedia
We present WikiTables, a Web application that enables users to interactively explore tabular knowledge extracted from Wikipedia by automatically joining together disparate tables to uncover "interesting" relationships. Expand
  • 50
  • 9
WINOGRANDE: An Adversarial Winograd Schema Challenge at Scale
We introduce WinoGrande, a large-scale dataset of 44k problems, inspired by the original WSC design, but adjusted to improve both the scale and the hardness of the dataset. Expand
  • 49
  • 9
Content-Based Citation Recommendation
We present a content-based method for recommending citations in an academic paper draft. Expand
  • 34
  • 8
Construction of the Literature Graph in Semantic Scholar
We describe a deployed scalable system for organizing published scientific literature into a heterogeneous graph to facilitate algorithmic manipulation and discovery. Expand
  • 78
  • 7
Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning
We introduce Cosmos QA, a large-scale dataset of 35,600 problems that require commonsense-based reading comprehension, formulated as multiple-choice questions that require reasoning beyond the exact text spans in the context. Expand
  • 39
  • 6
The AI2 system at SemEval-2017 Task 10 (ScienceIE): semi-supervised end-to-end entity and relation extraction
This paper describes our submission for the ScienceIE shared task (SemEval2017 Task 10) on entity and relation extraction from scientific papers. Expand
  • 40
  • 4
Abductive Commonsense Reasoning
In this paper, we present the first study that investigates the viability of language-based abductive reasoning. Expand
  • 24
  • 4