Abstract
Story comprehension requires a deep semantic understanding of the narrative, making it a challenging task. Inspired by previous studies on ROC Story Cloze Test, we propose a novel method, tracking various semantic aspects with external neural memory chains while encouraging each to focus on a particular semantic aspect. Evaluated on the task of story ending prediction, our model demonstrates superior performance to a collection of competitive baselines, setting a new state of the art.- Anthology ID:
- P18-2045
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 278–284
- Language:
- URL:
- https://aclanthology.org/P18-2045
- DOI:
- 10.18653/v1/P18-2045
- Cite (ACL):
- Fei Liu, Trevor Cohn, and Timothy Baldwin. 2018. Narrative Modeling with Memory Chains and Semantic Supervision. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 278–284, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Narrative Modeling with Memory Chains and Semantic Supervision (Liu et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/P18-2045.pdf
- Code
- liufly/narrative-modeling