@inproceedings{zhao-etal-2024-class-incremental,
title = "Class-Incremental Few-Shot Event Detection",
author = "Zhao, Kailin and
Jin, Xiaolong and
Bai, Long and
Guo, Jiafeng and
Cheng, Xueqi",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.290",
pages = "3261--3270",
abstract = "Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few labeled instances as it is time-consuming and labor-intensive to annotate a large number of unlabeled instances. Therefore, this paper proposes a new task, called class-incremental few-shot event detection. Nevertheless, there are two problems (i.e., old knowledge forgetting and new class overfitting) in this task. To solve these problems, this paper further presents a novel knowledge distillation and prompt learning based method, called Prompt-KD. Specifically, to reduce the forgetting issue about old knowledge, Prompt-KD develops an attention based multi-teacher knowledge distillation framework, where the ancestor teacher model pre-trained on base classes is reused in all learning sessions, and the father teacher model derives the current student model via adaptation. On the other hand, in order to cope with the few-shot learning scenario and alleviate the corresponding new class overfitting problem, Prompt-KD is also equipped with a prompt learning mechanism. Extensive experiments on two benchmark datasets, i.e., FewEvent and MAVEN, demonstrate the state-of-the-art performance of Prompt-KD.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2024-class-incremental">
<titleInfo>
<title>Class-Incremental Few-Shot Event Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kailin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaolong</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiafeng</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xueqi</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few labeled instances as it is time-consuming and labor-intensive to annotate a large number of unlabeled instances. Therefore, this paper proposes a new task, called class-incremental few-shot event detection. Nevertheless, there are two problems (i.e., old knowledge forgetting and new class overfitting) in this task. To solve these problems, this paper further presents a novel knowledge distillation and prompt learning based method, called Prompt-KD. Specifically, to reduce the forgetting issue about old knowledge, Prompt-KD develops an attention based multi-teacher knowledge distillation framework, where the ancestor teacher model pre-trained on base classes is reused in all learning sessions, and the father teacher model derives the current student model via adaptation. On the other hand, in order to cope with the few-shot learning scenario and alleviate the corresponding new class overfitting problem, Prompt-KD is also equipped with a prompt learning mechanism. Extensive experiments on two benchmark datasets, i.e., FewEvent and MAVEN, demonstrate the state-of-the-art performance of Prompt-KD.</abstract>
<identifier type="citekey">zhao-etal-2024-class-incremental</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.290</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3261</start>
<end>3270</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Class-Incremental Few-Shot Event Detection
%A Zhao, Kailin
%A Jin, Xiaolong
%A Bai, Long
%A Guo, Jiafeng
%A Cheng, Xueqi
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zhao-etal-2024-class-incremental
%X Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few labeled instances as it is time-consuming and labor-intensive to annotate a large number of unlabeled instances. Therefore, this paper proposes a new task, called class-incremental few-shot event detection. Nevertheless, there are two problems (i.e., old knowledge forgetting and new class overfitting) in this task. To solve these problems, this paper further presents a novel knowledge distillation and prompt learning based method, called Prompt-KD. Specifically, to reduce the forgetting issue about old knowledge, Prompt-KD develops an attention based multi-teacher knowledge distillation framework, where the ancestor teacher model pre-trained on base classes is reused in all learning sessions, and the father teacher model derives the current student model via adaptation. On the other hand, in order to cope with the few-shot learning scenario and alleviate the corresponding new class overfitting problem, Prompt-KD is also equipped with a prompt learning mechanism. Extensive experiments on two benchmark datasets, i.e., FewEvent and MAVEN, demonstrate the state-of-the-art performance of Prompt-KD.
%U https://aclanthology.org/2024.lrec-main.290
%P 3261-3270
Markdown (Informal)
[Class-Incremental Few-Shot Event Detection](https://aclanthology.org/2024.lrec-main.290) (Zhao et al., LREC-COLING 2024)
ACL
- Kailin Zhao, Xiaolong Jin, Long Bai, Jiafeng Guo, and Xueqi Cheng. 2024. Class-Incremental Few-Shot Event Detection. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3261–3270, Torino, Italia. ELRA and ICCL.