Open AccessProceedings Article
Commonsense causal reasoning using millions of personal stories
Andrew S. Gordon,Cosmin Adrian Bejan,Kenji Sagae +2 more
- pp 1180-1185
TLDR
Casting the commonsense causal reasoning problem as a Choice of Plausible Alternatives, four experiments that compare various statistical and information retrieval approaches to exploit causal information in story corpora are described.Abstract:
The personal stories that people write in their Internet weblogs include a substantial amount of information about the causal relationships between everyday events. In this paper we describe our efforts to use millions of these stories for automated commonsense causal reasoning. Casting the commonsense causal reasoning problem as a Choice of Plausible Alternatives, we describe four experiments that compare various statistical and information retrieval approaches to exploit causal information in story corpora. The top performing system in these experiments uses a simple co-occurrence statistic between words in the causal antecedent and consequent, calculated as the Pointwise Mutual Information between words in a corpus of millions of personal stories.read more
Citations
More filters
Posted Content
WINOGRANDE: An Adversarial Winograd Schema Challenge at Scale
TL;DR: The authors introduced WinoGrande, a large-scale dataset of 44k problems, inspired by the original Winograd Schema Challenge (WSC) design, but adjusted to improve both the scale and the hardness of the dataset.
Proceedings Article
Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning
TL;DR: The Choice Of Plausible Alternatives (COPA) evaluation as discussed by the authors uses a forced-choice format, where each question gives a premise and two plausible causes or effects, where the correct choice is the alternative that is more plausible than the other.
Proceedings Article
SemEval-2012 Task 7: Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning
TL;DR: The two systems that competed in this task as part of SemEval-2012 are described, and their results are compared to those achieved in previously published research.
Journal ArticleDOI
A Metaverse: Taxonomy, Components, Applications, and Open Challenges
TL;DR: This paper divides the concepts and essential techniques necessary for realizing the Metaverse into three components (i.e., hardware, software, and contents) and three approaches and describes essential methods based on three components and techniques to Metaverse’s representative Ready Player One, Roblox, and Facebook research in the domain of films, games, and studies.
Book
Computational Modeling of Narrative
TL;DR: This is the first book to provide a systematic foundation that integrates together narratology, AI, and computational linguistics and suggests a future characterized by advanced text mining of narrative structure from large-scale corpora and the development of a variety of useful authoring aids.
References
More filters
Journal ArticleDOI
Introduction to WordNet: An On-line Lexical Database
TL;DR: Standard alphabetical procedures for organizing lexical information put together words that are spelled alike and scatter words with similar or related meanings haphazardly through the list.
Journal ArticleDOI
Word association norms, mutual information, and lexicography
Kenneth Church,Patrick Hanks +1 more
TL;DR: The proposed measure, the association ratio, estimates word association norms directly from computer readable corpora, making it possible to estimate norms for tens of thousands of words.
Book
Handbook of Psycholinguistics
TL;DR: The authors, The Neuropsychology of language and its relationship with the human brain: A Guide to Research on the Perception of Speech and its Implications for Research and Theory, The authors.
Journal ArticleDOI
The Unreasonable Effectiveness of Data
TL;DR: A trillion-word corpus - along with other Web-derived corpora of millions, billions, or trillions of links, videos, images, tables, and user interactions - captures even very rare aspects of human behavior.