Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering

Lilian Wanzare, Alessandra Zarcone, Stefan Thater, Manfred Pinkal


Abstract
We present a semi-supervised clustering approach to induce script structure from crowdsourced descriptions of event sequences by grouping event descriptions into paraphrase sets (representing event types) and inducing their temporal order. Our approach exploits semantic and positional similarity and allows for flexible event order, thus overcoming the rigidity of previous approaches. We incorporate crowdsourced alignments as prior knowledge and show that exploiting a small number of alignments results in a substantial improvement in cluster quality over state-of-the-art models and provides an appropriate basis for the induction of temporal order. We also show a coverage study to demonstrate the scalability of our approach.
Anthology ID:
W17-0901
Volume:
Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Michael Roth, Nasrin Mostafazadeh, Nathanael Chambers, Annie Louis
Venue:
LSDSem
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–11
Language:
URL:
https://aclanthology.org/W17-0901
DOI:
10.18653/v1/W17-0901
Bibkey:
Cite (ACL):
Lilian Wanzare, Alessandra Zarcone, Stefan Thater, and Manfred Pinkal. 2017. Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering. In Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, pages 1–11, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering (Wanzare et al., LSDSem 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-0901.pdf
Data
OMICSROCStories