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 Test1 demonstrating an absolute improvement in accuracy of 4.7% over state-of-the-art implementations.
Cite
CITATION STYLE
Schenk, N., & Chiarcos, C. (2017). Resource-Lean Modeling of Coherence in Commonsense Stories. In LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop (pp. 68–73). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w17-0910
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
