An Encoder-decoder Approach to Predicting Causal Relations in Stories

Melissa Roemmele, Andrew Gordon


Abstract
We address the task of predicting causally related events in stories according to a standard evaluation framework, the Choice of Plausible Alternatives (COPA). We present a neural encoder-decoder model that learns to predict relations between adjacent sequences in stories as a means of modeling causality. We explore this approach using different methods for extracting and representing sequence pairs as well as different model architectures. We also compare the impact of different training datasets on our model. In particular, we demonstrate the usefulness of a corpus not previously applied to COPA, the ROCStories corpus. While not state-of-the-art, our results establish a new reference point for systems evaluated on COPA, and one that is particularly informative for future neural-based approaches.
Anthology ID:
W18-1506
Volume:
Proceedings of the First Workshop on Storytelling
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venues:
NAACL | Story-NLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
50–59
Language:
URL:
https://www.aclweb.org/anthology/W18-1506
DOI:
10.18653/v1/W18-1506
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W18-1506.pdf