Resource-lean modeling of coherence in commonsense stories

  • We present a resource-lean neural recognizer for modeling coherence in commonsense stories. Our lightweight system is inspired by successful attempts to modeling discourse relations and stands out due to its simplicity and easy optimization compared to prior approaches to narrative script learning. We evaluate our approach in the Story Cloze Test demonstrating an absolute improvement in accuracy of 4.7% over state-of-the-art implementations.

Download full text files

Export metadata

Statistics

Number of document requests

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Niko Schenk, Christian ChiarcosORCiDGND
URN:urn:nbn:de:bvb:384-opus4-1041198
Frontdoor URLhttps://opus.bibliothek.uni-augsburg.de/opus4/104119
ISBN:978-1-945626-40-1OPAC
Parent Title (English):Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, April 3, 2017, Valencia, Spain
Publisher:Association for Computational Linguistics
Place of publication:Stroudsburg, PA
Editor:Michael Roth, Nasrin Mostafazadeh, Nathanael Chambers, Annie Louis
Type:Conference Proceeding
Language:English
Year of first Publication:2017
Publishing Institution:Universität Augsburg
Release Date:2023/05/16
First Page:68
Last Page:73
DOI:https://doi.org/10.18653/v1/w17-0910
Institutes:Philologisch-Historische Fakultät
Philologisch-Historische Fakultät / Angewandte Computerlinguistik
Philologisch-Historische Fakultät / Angewandte Computerlinguistik / Lehrstuhl für Angewandte Computerlinguistik (ACoLi)
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):CC-BY 4.0: Creative Commons: Namensnennung (mit Print on Demand)

OPUS4 Logo