• Publications
  • Influence
SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge
TLDR
This report summarizes the results of the SemEval 2018 task on machine comprehension using commonsense knowledge. Expand
  • 90
  • 13
  • PDF
MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge
TLDR
We introduce a large dataset of narrative texts and questions about these texts, intended to be used in a machine comprehension task that requires reasoning using commonsense knowledge. Expand
  • 54
  • 11
  • PDF
InScript: Narrative texts annotated with script information
TLDR
This paper presents the InScript corpus (Narrative Texts Instantiating Script structure). Expand
  • 29
  • 5
  • PDF
Event Embeddings for Semantic Script Modeling
TLDR
We introduce a neural network model which relies on distributed compositional representations of events. Expand
  • 37
  • 4
  • PDF
Unsupervised Induction of Frame-Semantic Representations
TLDR
We extend an existing state-of-the-art Bayesian model for PropBank-style unsupervised semantic role induction (Titov and Klementiev, 2012) is extended to jointly induce semantic frames and their roles. Expand
  • 27
  • 4
  • PDF
Modeling Semantic Expectation: Using Script Knowledge for Referent Prediction
TLDR
We investigate the factors that affect human prediction by building a computational model that can predict upcoming discourse referents based on linguistic knowledge alone vs. common-sense knowledge. Expand
  • 21
  • 4
  • PDF
Inducing Neural Models of Script Knowledge
TLDR
In our method, distributed representations (i.e. vectors of real numbers) of event realizations are computed based on distributed representations of predicates and their arguments, and then the event representations are used in a ranker to predict the prototypical ordering of events. Expand
  • 54
  • 3
  • PDF
Learning to predict script events from domain-specific text
The automatic induction of scripts (Schank and Abelson, 1977) has been the focus of many recent works. In this paper, we employ a variety of these methods to learn Schank and Abelson’s canonicalExpand
  • 21
  • 3
  • PDF
Learning Semantic Script Knowledge with Event Embeddings
TLDR
In our method, the distributed representations (i.e. vectors of real numbers) of event realizations are computed based on distributed representations of predicates and their arguments, and then the event representations are used in a ranker to predict the expected ordering of events. Expand
  • 13
  • 3
  • PDF
Affect-Driven Dialog Generation
TLDR
We introduce EMOTIonal CONversational System (EMOTICONS), which generates emotionally diverse dialog responses based on the input dialog sequence and a predetermined target emotion. Expand
  • 24
  • 2
  • PDF
...
1
2
3
4
...