An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning

Markus Eberts, Adrian Ulges


Abstract
We present a joint model for entity-level relation extraction from documents. In contrast to other approaches - which focus on local intra-sentence mention pairs and thus require annotations on mention level - our model operates on entity level. To do so, a multi-task approach is followed that builds upon coreference resolution and gathers relevant signals via multi-instance learning with multi-level representations combining global entity and local mention information. We achieve state-of-the-art relation extraction results on the DocRED dataset and report the first entity-level end-to-end relation extraction results for future reference. Finally, our experimental results suggest that a joint approach is on par with task-specific learning, though more efficient due to shared parameters and training steps.
Anthology ID:
2021.eacl-main.319
Original:
2021.eacl-main.319v1
Version 2:
2021.eacl-main.319v2
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3650–3660
Language:
URL:
https://aclanthology.org/2021.eacl-main.319
DOI:
10.18653/v1/2021.eacl-main.319
Bibkey:
Cite (ACL):
Markus Eberts and Adrian Ulges. 2021. An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3650–3660, Online. Association for Computational Linguistics.
Cite (Informal):
An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning (Eberts & Ulges, EACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.eacl-main.319.pdf
Code
 lavis-nlp/jerex
Data
DocRED