Document-level Entity-based Extraction as Template Generation

Kung-Hsiang Huang, Sam Tang, Nanyun Peng


Abstract
Document-level entity-based extraction (EE), aiming at extracting entity-centric information such as entity roles and entity relations, is key to automatic knowledge acquisition from text corpora for various domains. Most document-level EE systems build extractive models, which struggle to model long-term dependencies among entities at the document level. To address this issue, we propose a generative framework for two document-level EE tasks: role-filler entity extraction (REE) and relation extraction (RE). We first formulate them as a template generation problem, allowing models to efficiently capture cross-entity dependencies, exploit label semantics, and avoid the exponential computation complexity of identifying N-ary relations. A novel cross-attention guided copy mechanism, TopK Copy, is incorporated into a pre-trained sequence-to-sequence model to enhance the capabilities of identifying key information in the input document. Experiments done on the MUC-4 and SciREX dataset show new state-of-the-art results on REE (+3.26%), binary RE (+4.8%), and 4-ary RE (+2.7%) in F1 score.
Anthology ID:
2021.emnlp-main.426
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5257–5269
Language:
URL:
https://aclanthology.org/2021.emnlp-main.426
DOI:
10.18653/v1/2021.emnlp-main.426
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.426.pdf
Code
 PlusLabNLP/TempGen
Data
MUC-4SciREX