Inducing Event Types and Roles in Reverse: Using Function to Discover Theme

Natalie Ahn


Abstract
With growing interest in automated event extraction, there is an increasing need to overcome the labor costs of hand-written event templates, entity lists, and annotated corpora. In the last few years, more inductive approaches have emerged, seeking to discover unknown event types and roles in raw text. The main recent efforts use probabilistic generative models, as in topic modeling, which are formally concise but do not always yield stable or easily interpretable results. We argue that event schema induction can benefit from greater structure in the process and in linguistic features that distinguish words’ functions and themes. To maximize our use of limited data, we reverse the typical schema induction steps and introduce new similarity measures, building an intuitive process for inducing the structure of unknown events.
Anthology ID:
W17-2710
Volume:
Proceedings of the Events and Stories in the News Workshop
Month:
August
Year:
2017
Address:
Vancouver, Canada
Venues:
EventStory | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
66–76
Language:
URL:
https://www.aclweb.org/anthology/W17-2710
DOI:
10.18653/v1/W17-2710
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-2710.pdf