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
- Venue:
- Story-NLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 50–59
- Language:
- URL:
- https://aclanthology.org/W18-1506
- DOI:
- 10.18653/v1/W18-1506
- Cite (ACL):
- Melissa Roemmele and Andrew Gordon. 2018. An Encoder-decoder Approach to Predicting Causal Relations in Stories. In Proceedings of the First Workshop on Storytelling, pages 50–59, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- An Encoder-decoder Approach to Predicting Causal Relations in Stories (Roemmele & Gordon, Story-NLP 2018)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/W18-1506.pdf
- Data
- COPA, ROCStories, VIST