Dense Event Ordering with a Multi-Pass Architecture

Nathanael Chambers, Taylor Cassidy, Bill McDowell, Steven Bethard


Abstract
The past 10 years of event ordering research has focused on learning partial orderings over document events and time expressions. The most popular corpus, the TimeBank, contains a small subset of the possible ordering graph. Many evaluations follow suit by only testing certain pairs of events (e.g., only main verbs of neighboring sentences). This has led most research to focus on specific learners for partial labelings. This paper attempts to nudge the discussion from identifying some relations to all relations. We present new experiments on strongly connected event graphs that contain ∼10 times more relations per document than the TimeBank. We also describe a shift away from the single learner to a sieve-based architecture that naturally blends multiple learners into a precision-ranked cascade of sieves. Each sieve adds labels to the event graph one at a time, and earlier sieves inform later ones through transitive closure. This paper thus describes innovations in both approach and task. We experiment on the densest event graphs to date and show a 14% gain over state-of-the-art.
Anthology ID:
Q14-1022
Volume:
Transactions of the Association for Computational Linguistics, Volume 2
Month:
Year:
2014
Address:
Venue:
TACL
SIG:
Publisher:
Note:
Pages:
273–284
Language:
URL:
https://www.aclweb.org/anthology/Q14-1022
DOI:
10.1162/tacl_a_00182
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/Q14-1022.pdf