Decomposing and Recomposing Event Structure

William Gantt, Lelia Glass, Aaron Steven White


Abstract
We present an event structure classification empirically derived from inferential properties annotated on sentence- and document-level Universal Decompositional Semantics (UDS) graphs. We induce this classification jointly with semantic role, entity, and event-event relation classifications using a document-level generative model structured by these graphs. To support this induction, we augment existing annotations found in the UDS1.0 dataset, which covers the entirety of the English Web Treebank, with an array of inferential properties capturing fine-grained aspects of the temporal and aspectual structure of events. The resulting dataset (available at decomp.io) is the largest annotation of event structure and (partial) event coreference to date.
Anthology ID:
2022.tacl-1.2
Volume:
Transactions of the Association for Computational Linguistics, Volume 10
Month:
Year:
2022
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
17–34
Language:
URL:
https://aclanthology.org/2022.tacl-1.2
DOI:
10.1162/tacl_a_00445
Bibkey:
Cite (ACL):
William Gantt, Lelia Glass, and Aaron Steven White. 2022. Decomposing and Recomposing Event Structure. Transactions of the Association for Computational Linguistics, 10:17–34.
Cite (Informal):
Decomposing and Recomposing Event Structure (Gantt et al., TACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.tacl-1.2.pdf