@inproceedings{anantheswaran-etal-2024-edm3,
title = "{EDM}3: Event Detection as Multi-task Text Generation",
author = "Anantheswaran, Ujjwala and
Gupta, Himanshu and
Parmar, Mihir and
Pal, Kuntal and
Baral, Chitta",
editor = "Bollegala, Danushka and
Shwartz, Vered",
booktitle = "Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.starsem-1.35",
doi = "10.18653/v1/2024.starsem-1.35",
pages = "438--451",
abstract = "We present EDM3, a novel approach for Event Detection (ED) based on decomposing and reformulating ED, and fine-tuning over its atomic subtasks. EDM3 enhances knowledge transfer while mitigating prediction error propagation inherent in pipelined approaches. EDM3 infers dataset-specific knowledge required for the complex primary task from its atomic tasks, making it adaptable to any set of event types. We evaluate EDM3 on multiple ED datasets, achieving state-of-the-art results on RAMS (71.3{\%} vs 65.1{\%} F1), and competitive performance on WikiEvents, MAVEN (∆ = 0.2{\%}), and MLEE (∆ = 1.8{\%}). We present an ablation study over rare event types ({\textless}15 instances in training data) in MAVEN, where EDM3 achieves {\textasciitilde}90{\%} F1. To the best of the authors{'} knowledge, we are the first to analyze ED performance over non-standard event configurations (i.e., multi-word and multi-class triggers). Experimental results show that EDM3 achieves {\textasciitilde}90{\%} exact match accuracy on multi-word triggers and {\textasciitilde}61{\%} prediction accuracy on multi-class triggers. This work establishes the effectiveness of EDM3 in enhancing performance on a complex information extraction task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="anantheswaran-etal-2024-edm3">
<titleInfo>
<title>EDM3: Event Detection as Multi-task Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ujjwala</namePart>
<namePart type="family">Anantheswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Himanshu</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihir</namePart>
<namePart type="family">Parmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuntal</namePart>
<namePart type="family">Pal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chitta</namePart>
<namePart type="family">Baral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danushka</namePart>
<namePart type="family">Bollegala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present EDM3, a novel approach for Event Detection (ED) based on decomposing and reformulating ED, and fine-tuning over its atomic subtasks. EDM3 enhances knowledge transfer while mitigating prediction error propagation inherent in pipelined approaches. EDM3 infers dataset-specific knowledge required for the complex primary task from its atomic tasks, making it adaptable to any set of event types. We evaluate EDM3 on multiple ED datasets, achieving state-of-the-art results on RAMS (71.3% vs 65.1% F1), and competitive performance on WikiEvents, MAVEN (∆ = 0.2%), and MLEE (∆ = 1.8%). We present an ablation study over rare event types (\textless15 instances in training data) in MAVEN, where EDM3 achieves ~90% F1. To the best of the authors’ knowledge, we are the first to analyze ED performance over non-standard event configurations (i.e., multi-word and multi-class triggers). Experimental results show that EDM3 achieves ~90% exact match accuracy on multi-word triggers and ~61% prediction accuracy on multi-class triggers. This work establishes the effectiveness of EDM3 in enhancing performance on a complex information extraction task.</abstract>
<identifier type="citekey">anantheswaran-etal-2024-edm3</identifier>
<identifier type="doi">10.18653/v1/2024.starsem-1.35</identifier>
<location>
<url>https://aclanthology.org/2024.starsem-1.35</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>438</start>
<end>451</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EDM3: Event Detection as Multi-task Text Generation
%A Anantheswaran, Ujjwala
%A Gupta, Himanshu
%A Parmar, Mihir
%A Pal, Kuntal
%A Baral, Chitta
%Y Bollegala, Danushka
%Y Shwartz, Vered
%S Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F anantheswaran-etal-2024-edm3
%X We present EDM3, a novel approach for Event Detection (ED) based on decomposing and reformulating ED, and fine-tuning over its atomic subtasks. EDM3 enhances knowledge transfer while mitigating prediction error propagation inherent in pipelined approaches. EDM3 infers dataset-specific knowledge required for the complex primary task from its atomic tasks, making it adaptable to any set of event types. We evaluate EDM3 on multiple ED datasets, achieving state-of-the-art results on RAMS (71.3% vs 65.1% F1), and competitive performance on WikiEvents, MAVEN (∆ = 0.2%), and MLEE (∆ = 1.8%). We present an ablation study over rare event types (\textless15 instances in training data) in MAVEN, where EDM3 achieves ~90% F1. To the best of the authors’ knowledge, we are the first to analyze ED performance over non-standard event configurations (i.e., multi-word and multi-class triggers). Experimental results show that EDM3 achieves ~90% exact match accuracy on multi-word triggers and ~61% prediction accuracy on multi-class triggers. This work establishes the effectiveness of EDM3 in enhancing performance on a complex information extraction task.
%R 10.18653/v1/2024.starsem-1.35
%U https://aclanthology.org/2024.starsem-1.35
%U https://doi.org/10.18653/v1/2024.starsem-1.35
%P 438-451
Markdown (Informal)
[EDM3: Event Detection as Multi-task Text Generation](https://aclanthology.org/2024.starsem-1.35) (Anantheswaran et al., *SEM 2024)
ACL
- Ujjwala Anantheswaran, Himanshu Gupta, Mihir Parmar, Kuntal Pal, and Chitta Baral. 2024. EDM3: Event Detection as Multi-task Text Generation. In Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024), pages 438–451, Mexico City, Mexico. Association for Computational Linguistics.