Connecting the Dots: Event Graph Schema Induction with Path Language Modeling

Manling Li, Qi Zeng, Ying Lin, Kyunghyun Cho, Heng Ji, Jonathan May, Nathanael Chambers, Clare Voss


Abstract
Event schemas can guide our understanding and ability to make predictions with respect to what might happen next. We propose a new Event Graph Schema, where two event types are connected through multiple paths involving entities that fill important roles in a coherent story. We then introduce Path Language Model, an auto-regressive language model trained on event-event paths, and select salient and coherent paths to probabilistically construct these graph schemas. We design two evaluation metrics, instance coverage and instance coherence, to evaluate the quality of graph schema induction, by checking when coherent event instances are covered by the schema graph. Intrinsic evaluations show that our approach is highly effective at inducing salient and coherent schemas. Extrinsic evaluations show the induced schema repository provides significant improvement to downstream end-to-end Information Extraction over a state-of-the-art joint neural extraction model, when used as additional global features to unfold instance graphs.
Anthology ID:
2020.emnlp-main.50
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
684–695
Language:
URL:
https://www.aclweb.org/anthology/2020.emnlp-main.50
DOI:
10.18653/v1/2020.emnlp-main.50
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.emnlp-main.50.pdf