Machine Reading of Historical Events

Or Honovich, Lucas Torroba Hennigen, Omri Abend, Shay B. Cohen


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
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7486–7497
Language:
URL:
https://www.aclweb.org/anthology/2020.acl-main.668
DOI:
10.18653/v1/2020.acl-main.668
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.acl-main.668.pdf
Video:
 http://slideslive.com/38929364