Resource-Lean Modeling of Coherence in Commonsense Stories

Niko Schenk, Christian Chiarcos


Abstract
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.
Anthology ID:
W17-0910
Volume:
Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Michael Roth, Nasrin Mostafazadeh, Nathanael Chambers, Annie Louis
Venue:
LSDSem
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
68–73
Language:
URL:
https://aclanthology.org/W17-0910
DOI:
10.18653/v1/W17-0910
Bibkey:
Cite (ACL):
Niko Schenk and Christian Chiarcos. 2017. Resource-Lean Modeling of Coherence in Commonsense Stories. In Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, pages 68–73, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Resource-Lean Modeling of Coherence in Commonsense Stories (Schenk & Chiarcos, LSDSem 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-0910.pdf
Data
ROCStories