Template Filling with Generative Transformers

Xinya Du, Alexander Rush, Claire Cardie


Abstract
Template filling is generally tackled by a pipeline of two separate supervised systems – one for role-filler extraction and another for template/event recognition. Since pipelines consider events in isolation, they can suffer from error propagation. We introduce a framework based on end-to-end generative transformers for this task (i.e., GTT). It naturally models the dependence between entities both within a single event and across the multiple events described in a document. Experiments demonstrate that this framework substantially outperforms pipeline-based approaches, and other neural end-to-end baselines that do not model between-event dependencies. We further show that our framework specifically improves performance on documents containing multiple events.
Anthology ID:
2021.naacl-main.70
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
909–914
Language:
URL:
https://aclanthology.org/2021.naacl-main.70
DOI:
10.18653/v1/2021.naacl-main.70
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.70.pdf