@inproceedings{huang-etal-2024-distill-fuse,
title = "Distill, Fuse, Pre-train: Towards Effective Event Causality Identification with Commonsense-Aware Pre-trained Model",
author = "Huang, Peixin and
Zhao, Xiang and
Hu, Minghao and
Tan, Zhen and
Xiao, Weidong",
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.450",
pages = "5029--5040",
abstract = "Event Causality Identification (ECI) aims to detect causal relations between events in unstructured texts. This task is challenged by the lack of data and explicit causal clues. Some methods incorporate explicit knowledge from external knowledge graphs (KGs) into Pre-trained Language Models (PLMs) to tackle these issues, achieving certain accomplishments. However, they ignore that existing KGs usually contain trivial knowledge which may prejudice the performance. Moreover, they simply integrate the concept triplets, underutilizing the deep interaction between the text and external graph. In this paper, we propose an effective pipeline DFP, i.e., Distill, Fuse and Pre-train, to build a commonsense-aware pre-trained model which integrates reliable task-specific knowledge from commonsense graphs. This pipeline works as follows: (1) To leverage the reliable knowledge, commonsense graph distillation is proposed to distill commonsense graphs and obtain the meta-graph which contain credible task-oriented knowledge. (2) To model the deep interaction between the text and external graph, heterogeneous information fusion is proposed to fuse them through a commonsense-aware memory network. (3) Continual pre-training designs three continual pre-training tasks to further align and fuse the text and the commonsense meta-graph. Through extensive experiments on two benchmarks, we demonstrate the validity of our pipeline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2024-distill-fuse">
<titleInfo>
<title>Distill, Fuse, Pre-train: Towards Effective Event Causality Identification with Commonsense-Aware Pre-trained Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peixin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghao</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weidong</namePart>
<namePart type="family">Xiao</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 Causality Identification (ECI) aims to detect causal relations between events in unstructured texts. This task is challenged by the lack of data and explicit causal clues. Some methods incorporate explicit knowledge from external knowledge graphs (KGs) into Pre-trained Language Models (PLMs) to tackle these issues, achieving certain accomplishments. However, they ignore that existing KGs usually contain trivial knowledge which may prejudice the performance. Moreover, they simply integrate the concept triplets, underutilizing the deep interaction between the text and external graph. In this paper, we propose an effective pipeline DFP, i.e., Distill, Fuse and Pre-train, to build a commonsense-aware pre-trained model which integrates reliable task-specific knowledge from commonsense graphs. This pipeline works as follows: (1) To leverage the reliable knowledge, commonsense graph distillation is proposed to distill commonsense graphs and obtain the meta-graph which contain credible task-oriented knowledge. (2) To model the deep interaction between the text and external graph, heterogeneous information fusion is proposed to fuse them through a commonsense-aware memory network. (3) Continual pre-training designs three continual pre-training tasks to further align and fuse the text and the commonsense meta-graph. Through extensive experiments on two benchmarks, we demonstrate the validity of our pipeline.</abstract>
<identifier type="citekey">huang-etal-2024-distill-fuse</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.450</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>5029</start>
<end>5040</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Distill, Fuse, Pre-train: Towards Effective Event Causality Identification with Commonsense-Aware Pre-trained Model
%A Huang, Peixin
%A Zhao, Xiang
%A Hu, Minghao
%A Tan, Zhen
%A Xiao, Weidong
%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 huang-etal-2024-distill-fuse
%X Event Causality Identification (ECI) aims to detect causal relations between events in unstructured texts. This task is challenged by the lack of data and explicit causal clues. Some methods incorporate explicit knowledge from external knowledge graphs (KGs) into Pre-trained Language Models (PLMs) to tackle these issues, achieving certain accomplishments. However, they ignore that existing KGs usually contain trivial knowledge which may prejudice the performance. Moreover, they simply integrate the concept triplets, underutilizing the deep interaction between the text and external graph. In this paper, we propose an effective pipeline DFP, i.e., Distill, Fuse and Pre-train, to build a commonsense-aware pre-trained model which integrates reliable task-specific knowledge from commonsense graphs. This pipeline works as follows: (1) To leverage the reliable knowledge, commonsense graph distillation is proposed to distill commonsense graphs and obtain the meta-graph which contain credible task-oriented knowledge. (2) To model the deep interaction between the text and external graph, heterogeneous information fusion is proposed to fuse them through a commonsense-aware memory network. (3) Continual pre-training designs three continual pre-training tasks to further align and fuse the text and the commonsense meta-graph. Through extensive experiments on two benchmarks, we demonstrate the validity of our pipeline.
%U https://aclanthology.org/2024.lrec-main.450
%P 5029-5040
Markdown (Informal)
[Distill, Fuse, Pre-train: Towards Effective Event Causality Identification with Commonsense-Aware Pre-trained Model](https://aclanthology.org/2024.lrec-main.450) (Huang et al., LREC-COLING 2024)
ACL
- Peixin Huang, Xiang Zhao, Minghao Hu, Zhen Tan, and Weidong Xiao. 2024. Distill, Fuse, Pre-train: Towards Effective Event Causality Identification with Commonsense-Aware Pre-trained Model. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5029–5040, Torino, Italia. ELRA and ICCL.