@inproceedings{le-etal-2024-sharpseq,
title = "{S}harp{S}eq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning",
author = "Le, Thanh-Thien and
Dao, Viet and
Nguyen, Linh and
Nguyen, Thi-Nhung and
Ngo, Linh and
Nguyen, Thien",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.200",
doi = "10.18653/v1/2024.naacl-long.200",
pages = "3632--3644",
abstract = "Continual event detection is a cornerstone in uncovering valuable patterns in many dynamic practical applications, where novel events emerge daily. Existing state-of-the-art approaches with replay buffers still suffer from catastrophic forgetting, partially due to overly simplistic objective aggregation. This oversight disregards complex trade-offs and leads to sub-optimal gradient updates, resulting in performance deterioration across objectives. While there are successful, widely cited multi-objective optimization frameworks for multi-task learning, they lack mechanisms to address data imbalance and evaluate whether a Pareto-optimal solution can effectively mitigate catastrophic forgetting, rendering them unsuitable for direct application to continual learning. To address these challenges, we propose **SharpSeq**, a novel continual learning paradigm leveraging sharpness-aware minimization combined with a generative model to balance training data distribution. Through extensive experiments on multiple real-world datasets, we demonstrate the superior performance of SharpSeq in continual event detection, proving the importance of our approach in mitigating catastrophic forgetting in continual event detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-etal-2024-sharpseq">
<titleInfo>
<title>SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning</title>
</titleInfo>
<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">Viet</namePart>
<namePart type="family">Dao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thi-Nhung</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linh</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="family">Nguyen</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 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</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>Continual event detection is a cornerstone in uncovering valuable patterns in many dynamic practical applications, where novel events emerge daily. Existing state-of-the-art approaches with replay buffers still suffer from catastrophic forgetting, partially due to overly simplistic objective aggregation. This oversight disregards complex trade-offs and leads to sub-optimal gradient updates, resulting in performance deterioration across objectives. While there are successful, widely cited multi-objective optimization frameworks for multi-task learning, they lack mechanisms to address data imbalance and evaluate whether a Pareto-optimal solution can effectively mitigate catastrophic forgetting, rendering them unsuitable for direct application to continual learning. To address these challenges, we propose **SharpSeq**, a novel continual learning paradigm leveraging sharpness-aware minimization combined with a generative model to balance training data distribution. Through extensive experiments on multiple real-world datasets, we demonstrate the superior performance of SharpSeq in continual event detection, proving the importance of our approach in mitigating catastrophic forgetting in continual event detection.</abstract>
<identifier type="citekey">le-etal-2024-sharpseq</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.200</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.200</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>3632</start>
<end>3644</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning
%A Le, Thanh-Thien
%A Dao, Viet
%A Nguyen, Linh
%A Nguyen, Thi-Nhung
%A Ngo, Linh
%A Nguyen, Thien
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F le-etal-2024-sharpseq
%X Continual event detection is a cornerstone in uncovering valuable patterns in many dynamic practical applications, where novel events emerge daily. Existing state-of-the-art approaches with replay buffers still suffer from catastrophic forgetting, partially due to overly simplistic objective aggregation. This oversight disregards complex trade-offs and leads to sub-optimal gradient updates, resulting in performance deterioration across objectives. While there are successful, widely cited multi-objective optimization frameworks for multi-task learning, they lack mechanisms to address data imbalance and evaluate whether a Pareto-optimal solution can effectively mitigate catastrophic forgetting, rendering them unsuitable for direct application to continual learning. To address these challenges, we propose **SharpSeq**, a novel continual learning paradigm leveraging sharpness-aware minimization combined with a generative model to balance training data distribution. Through extensive experiments on multiple real-world datasets, we demonstrate the superior performance of SharpSeq in continual event detection, proving the importance of our approach in mitigating catastrophic forgetting in continual event detection.
%R 10.18653/v1/2024.naacl-long.200
%U https://aclanthology.org/2024.naacl-long.200
%U https://doi.org/10.18653/v1/2024.naacl-long.200
%P 3632-3644
Markdown (Informal)
[SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning](https://aclanthology.org/2024.naacl-long.200) (Le et al., NAACL 2024)
ACL