Towards Open Domain Event Trigger Identification using Adversarial Domain Adaptation

Aakanksha Naik, Carolyn Rose


Abstract
We tackle the task of building supervised event trigger identification models which can generalize better across domains. Our work leverages the adversarial domain adaptation (ADA) framework to introduce domain-invariance. ADA uses adversarial training to construct representations that are predictive for trigger identification, but not predictive of the example’s domain. It requires no labeled data from the target domain, making it completely unsupervised. Experiments with two domains (English literature and news) show that ADA leads to an average F1 score improvement of 3.9 on out-of-domain data. Our best performing model (BERT-A) reaches 44-49 F1 across both domains, using no labeled target data. Preliminary experiments reveal that finetuning on 1% labeled data, followed by self-training leads to substantial improvement, reaching 51.5 and 67.2 F1 on literature and news respectively.
Anthology ID:
2020.acl-main.681
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7618–7624
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.acl-main.681/
DOI:
10.18653/v1/2020.acl-main.681
Bibkey:
Cite (ACL):
Aakanksha Naik and Carolyn Rose. 2020. Towards Open Domain Event Trigger Identification using Adversarial Domain Adaptation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7618–7624, Online. Association for Computational Linguistics.
Cite (Informal):
Towards Open Domain Event Trigger Identification using Adversarial Domain Adaptation (Naik & Rose, ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.acl-main.681.pdf
Video:
 http://slideslive.com/38929304
Code
 aakanksha19/ODETTE