@inproceedings{dao-etal-2024-lifelong,
title = "Lifelong Event Detection via Optimal Transport",
author = "Dao, Viet and
Pham, Van-Cuong and
Tran, Quyen and
Le, Thanh-Thien and
Ngo, Linh Van and
Nguyen, Thien Huu",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.701",
doi = "10.18653/v1/2024.emnlp-main.701",
pages = "12610--12621",
abstract = "Continual Event Detection (CED) poses a formidable challenge due to the catastrophic forgetting phenomenon, where learning new tasks (with new coming event types) hampers performance on previous ones. In this paper, we introduce a novel approach, Lifelong Event Detection via Optimal Transport (**LEDOT**), that leverages optimal transport principles to align the optimization of our classification module with the intrinsic nature of each class, as defined by their pre-trained language modeling. Our method integrates replay sets, prototype latent representations, and an innovative Optimal Transport component. Extensive experiments on MAVEN and ACE datasets demonstrate LEDOT{'}s superior performance, consistently outperforming state-of-the-art baselines. The results underscore LEDOT as a pioneering solution in continual event detection, offering a more effective and nuanced approach to addressing catastrophic forgetting in evolving environments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dao-etal-2024-lifelong">
<titleInfo>
<title>Lifelong Event Detection via Optimal Transport</title>
</titleInfo>
<name type="personal">
<namePart type="given">Viet</namePart>
<namePart type="family">Dao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Van-Cuong</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quyen</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh-Thien</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linh</namePart>
<namePart type="given">Van</namePart>
<namePart type="family">Ngo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="given">Huu</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Continual Event Detection (CED) poses a formidable challenge due to the catastrophic forgetting phenomenon, where learning new tasks (with new coming event types) hampers performance on previous ones. In this paper, we introduce a novel approach, Lifelong Event Detection via Optimal Transport (**LEDOT**), that leverages optimal transport principles to align the optimization of our classification module with the intrinsic nature of each class, as defined by their pre-trained language modeling. Our method integrates replay sets, prototype latent representations, and an innovative Optimal Transport component. Extensive experiments on MAVEN and ACE datasets demonstrate LEDOT’s superior performance, consistently outperforming state-of-the-art baselines. The results underscore LEDOT as a pioneering solution in continual event detection, offering a more effective and nuanced approach to addressing catastrophic forgetting in evolving environments.</abstract>
<identifier type="citekey">dao-etal-2024-lifelong</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.701</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.701</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>12610</start>
<end>12621</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lifelong Event Detection via Optimal Transport
%A Dao, Viet
%A Pham, Van-Cuong
%A Tran, Quyen
%A Le, Thanh-Thien
%A Ngo, Linh Van
%A Nguyen, Thien Huu
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F dao-etal-2024-lifelong
%X Continual Event Detection (CED) poses a formidable challenge due to the catastrophic forgetting phenomenon, where learning new tasks (with new coming event types) hampers performance on previous ones. In this paper, we introduce a novel approach, Lifelong Event Detection via Optimal Transport (**LEDOT**), that leverages optimal transport principles to align the optimization of our classification module with the intrinsic nature of each class, as defined by their pre-trained language modeling. Our method integrates replay sets, prototype latent representations, and an innovative Optimal Transport component. Extensive experiments on MAVEN and ACE datasets demonstrate LEDOT’s superior performance, consistently outperforming state-of-the-art baselines. The results underscore LEDOT as a pioneering solution in continual event detection, offering a more effective and nuanced approach to addressing catastrophic forgetting in evolving environments.
%R 10.18653/v1/2024.emnlp-main.701
%U https://aclanthology.org/2024.emnlp-main.701
%U https://doi.org/10.18653/v1/2024.emnlp-main.701
%P 12610-12621
Markdown (Informal)
[Lifelong Event Detection via Optimal Transport](https://aclanthology.org/2024.emnlp-main.701) (Dao et al., EMNLP 2024)
ACL
- Viet Dao, Van-Cuong Pham, Quyen Tran, Thanh-Thien Le, Linh Van Ngo, and Thien Huu Nguyen. 2024. Lifelong Event Detection via Optimal Transport. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12610–12621, Miami, Florida, USA. Association for Computational Linguistics.