Abstract
Machine reading is an ambitious goal in NLP that subsumes a wide range of text understanding capabilities. Within this broad framework, we address the task of machine reading the time of historical events, compile datasets for the task, and develop a model for tackling it. Given a brief textual description of an event, we show that good performance can be achieved by extracting relevant sentences from Wikipedia, and applying a combination of task-specific and general-purpose feature embeddings for the classification. Furthermore, we establish a link between the historical event ordering task and the event focus time task from the information retrieval literature, showing they also provide a challenging test case for machine reading algorithms.- Anthology ID:
- 2020.acl-main.668
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7486–7497
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.668
- DOI:
- 10.18653/v1/2020.acl-main.668
- Cite (ACL):
- Or Honovich, Lucas Torroba Hennigen, Omri Abend, and Shay B. Cohen. 2020. Machine Reading of Historical Events. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7486–7497, Online. Association for Computational Linguistics.
- Cite (Informal):
- Machine Reading of Historical Events (Honovich et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.668.pdf
- Code
- ltorroba/machine-reading-historical-events