Semi-supervised New Event Type Induction and Event Detection

Lifu Huang, Heng Ji


Abstract
Most previous event extraction studies assume a set of target event types and corresponding event annotations are given, which could be very expensive. In this paper, we work on a new task of semi-supervised event type induction, aiming to automatically discover a set of unseen types from a given corpus by leveraging annotations available for a few seen types. We design a Semi-Supervised Vector Quantized Variational Autoencoder framework to automatically learn a discrete latent type representation for each seen and unseen type and optimize them using seen type event annotations. A variational autoencoder is further introduced to enforce the reconstruction of each event mention conditioned on its latent type distribution. Experiments show that our approach can not only achieve state-of-the-art performance on supervised event detection but also discover high-quality new event types.
Anthology ID:
2020.emnlp-main.53
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
718–724
Language:
URL:
https://aclanthology.org/2020.emnlp-main.53
DOI:
10.18653/v1/2020.emnlp-main.53
Bibkey:
Cite (ACL):
Lifu Huang and Heng Ji. 2020. Semi-supervised New Event Type Induction and Event Detection. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 718–724, Online. Association for Computational Linguistics.
Cite (Informal):
Semi-supervised New Event Type Induction and Event Detection (Huang & Ji, EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2020.emnlp-main.53.pdf
Video:
 https://slideslive.com/38939118