Abstract
This paper presents a corpus and experimental results to extract possession relations over time. We work with Wikipedia articles about artworks, and extract possession relations along with temporal information indicating when these relations are true. The annotation scheme yields many possessors over time for a given artwork, and experimental results show that an LSTM ensemble can automate the task.- Anthology ID:
- D18-1251
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2278–2287
- Language:
- URL:
- https://aclanthology.org/D18-1251
- DOI:
- 10.18653/v1/D18-1251
- Cite (ACL):
- Dhivya Chinnappa and Eduardo Blanco. 2018. Possessors Change Over Time: A Case Study with Artworks. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2278–2287, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Possessors Change Over Time: A Case Study with Artworks (Chinnappa & Blanco, EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/D18-1251.pdf