Abstract
The standard approach for inducing narrative chains considers statistics gathered per individual document. We consider whether statistics gathered using cross-document relations can lead to improved chain induction. Our study is motivated by legal narratives, where cases typically cite thematically similar cases. We consider four novel variations on pointwise mutual information (PMI), each accounting for cross-document relations in a different way. One proposed PMI variation performs 58% better relative to standard PMI on recall@50 and induces qualitatively better narrative chains.- Anthology ID:
- 2022.starsem-1.18
- Volume:
- Proceedings of the 11th Joint Conference on Lexical and Computational Semantics
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, Washington
- Venue:
- *SEM
- SIG:
- SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 208–212
- Language:
- URL:
- https://aclanthology.org/2022.starsem-1.18
- DOI:
- 10.18653/v1/2022.starsem-1.18
- Cite (ACL):
- Andrew Blair-stanek and Benjamin Van Durme. 2022. Improved Induction of Narrative Chains via Cross-Document Relations. In Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, pages 208–212, Seattle, Washington. Association for Computational Linguistics.
- Cite (Informal):
- Improved Induction of Narrative Chains via Cross-Document Relations (Blair-stanek & Van Durme, *SEM 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.starsem-1.18.pdf
- Code
- blairstanek/cross-doc