Exploring Entities in Event Detection as Question Answering

descriptionPublicationkeyboard_double_arrow_right Part of book or chapter of book , Article , Conference object 01 Jan 2022 France English Publisher:Springer International PublishingFunded by:EC | EMBEDDIA, EC | NewsEye

Authors: Boros, Emanuela; Moreno, Jose G.; Doucet, Antoine;

doi: 10.1007/978-3-030-99736-6_5 , 10.5281/zenodo.5779941 , 10.5281/zenodo.6425904 , 10.5281/zenodo.5779940 , 10.5281/zenodo.6425903

Exploring Entities in Event Detection as Question Answering

- Summary
- Subjects
- Metrics

Abstract

In this paper, we approach a recent and under-researched paradigm for the task of event detection (ED) by casting it as a question-answering (QA) problem with the possibility of multiple answers and the support of entities. The extraction of event triggers is, thus, transformed into the task of identifying answer spans from a context, while also focusing on the surrounding entities. The architecture is based on a pre-trained and fine-tuned language model, where the input context is augmented with entities marked at different levels, their positions, their types, and, finally, their argument roles. Experiments on the ACE 2005 corpus demonstrate that the proposed model properly leverages entity information in detecting events and that it is a viable solution for the ED task. Moreover, we demonstrate that our method with different entity markers is particularly able to extract unseen event types in few-shot learning settings.

Country

France

Related Organizations

View all View all

Keywords

[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Few-shot learning, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Event detection, Question answering, Few-shot learning., [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 004, [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], [INFO.INFO-DL]Computer Science [cs]/Digital Libraries [cs.DL], Question answering, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], Event detection, [INFO.INFO-IR] Computer Science [cs]/Information Retrieval [cs.IR], [INFO.INFO-DL] Computer Science [cs]/Digital Libraries [cs.DL], [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC]

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	1
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average