Joint Extraction of Entities, Relations, and Events via Modeling Inter-Instance and Inter-Label Dependencies

June 16, 2022 Natural Language Processing

Joint Extraction of Entities, Relations, and Events via Modeling Inter-Instance and Inter-Label Dependencies

41 minutes
Minh Van Nguyen, Bonan Min, Franck Dernoncourt and Thien Huu Nguyen
NAACL 2022

Download

Abstract

Event trigger detection, entity mention recognition, event argument extraction, and relation extraction are the four important tasks in information extraction that have been performed jointly (Joint Information Extraction – JointIE) to avoid error propagation and leverage dependencies between the task instances (i.e., event triggers, entity mentions, relations, and event arguments). However, previous JointIE models often assume heuristic manually-designed dependency between the task instances and mean-field factorization for the joint distribution of instance labels, thus unable to capture optimal dependencies among instances and labels to improve representation learning and IE performance. To overcome these limitations, we propose to induce a dependency graph among task instances from data to boost representation learning. To better capture dependencies between instance labels, we propose to directly estimate their joint distribution via Conditional Random Fields. Noise Contrastive Estimation is introduced to address the maximization of the intractable joint likelihood for model training. Finally, to improve the decoding with greedy or beam search in prior work, we present Simulated Annealing to better find the globally optimal assignment for instance labels at decoding time. Experimental results show that our proposed model outperforms previous models on multiple IE tasks across 5 datasets and 2 languages.

Bibtex

@inproceedings{nguyen-etal-2022-joint,
title = “”Joint Extraction of Entities, Relations, and Events via Modeling Inter-Instance and Inter-Label Dependencies””,
author = “”Nguyen, Minh Van and
Min, Bonan and
Dernoncourt, Franck and
Nguyen, Thien””,
booktitle = “”Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies””,
month = jul,
year = “”2022″”,
address = “”Seattle, United States””,
publisher = “”Association for Computational Linguistics””,
url = “”https://aclanthology.org/2022.naacl-main.324″”,
pages = “”4363–4374″”,
abstract = “”Event trigger detection, entity mention recognition, event argument extraction, and relation extraction are the four important tasks in information extraction that have been performed jointly (Joint Information Extraction – JointIE) to avoid error propagation and leverage dependencies between the task instances (i.e., event triggers, entity mentions, relations, and event arguments). However, previous JointIE models often assume heuristic manually-designed dependency between the task instances and mean-field factorization for the joint distribution of instance labels, thus unable to capture optimal dependencies among instances and labels to improve representation learning and IE performance. To overcome these limitations, we propose to induce a dependency graph among task instances from data to boost representation learning. To better capture dependencies between instance labels, we propose to directly estimate their joint distribution via Conditional Random Fields. Noise Contrastive Estimation is introduced to address the maximization of the intractable joint likelihood for model training. Finally, to improve the decoding with greedy or beam search in prior work, we present Simulated Annealing to better find the globally optimal assignment for instance labels at decoding time. Experimental results show that our proposed model outperforms previous models on multiple IE tasks across 5 datasets and 2 languages.””,
}