@inproceedings{lu-etal-2024-automatic-construction,
title = "Automatic Construction of a {C}hinese Review Dataset for Aspect Sentiment Triplet Extraction via Iterative Weak Supervision",
author = "Lu, Chia-Wen and
Yang, Ching-Wen and
Ma, Wei-Yun",
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.167",
pages = "1871--1882",
abstract = "Aspect Sentiment Triplet Extraction (ASTE), introduced in 2020, is a task that involves the extraction of three key elements: target aspects, descriptive opinion spans, and their corresponding sentiment polarity. This process, however, faces a significant hurdle, particularly when applied to Chinese languages, due to the lack of sufficient datasets for model training, largely attributable to the arduous manual labeling process. To address this issue, we present an innovative framework that facilitates the automatic construction of ASTE via Iterative Weak Supervision, negating the need for manual labeling, aided by a discriminator to weed out subpar samples. The objective is to successively improve the quality of this raw data and generate supplementary data. The effectiveness of our approach is underscored by our results, which include the creation of a substantial Chinese review dataset. This dataset encompasses over 60,000 Google restaurant reviews in Chinese and features more than 200,000 extracted triplets. Moreover, we have also established a robust baseline model by leveraging a novel method of weak supervision. Both our dataset and model are openly accessible to the public.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2024-automatic-construction">
<titleInfo>
<title>Automatic Construction of a Chinese Review Dataset for Aspect Sentiment Triplet Extraction via Iterative Weak Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chia-Wen</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ching-Wen</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Yun</namePart>
<namePart type="family">Ma</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>Aspect Sentiment Triplet Extraction (ASTE), introduced in 2020, is a task that involves the extraction of three key elements: target aspects, descriptive opinion spans, and their corresponding sentiment polarity. This process, however, faces a significant hurdle, particularly when applied to Chinese languages, due to the lack of sufficient datasets for model training, largely attributable to the arduous manual labeling process. To address this issue, we present an innovative framework that facilitates the automatic construction of ASTE via Iterative Weak Supervision, negating the need for manual labeling, aided by a discriminator to weed out subpar samples. The objective is to successively improve the quality of this raw data and generate supplementary data. The effectiveness of our approach is underscored by our results, which include the creation of a substantial Chinese review dataset. This dataset encompasses over 60,000 Google restaurant reviews in Chinese and features more than 200,000 extracted triplets. Moreover, we have also established a robust baseline model by leveraging a novel method of weak supervision. Both our dataset and model are openly accessible to the public.</abstract>
<identifier type="citekey">lu-etal-2024-automatic-construction</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.167</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1871</start>
<end>1882</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Construction of a Chinese Review Dataset for Aspect Sentiment Triplet Extraction via Iterative Weak Supervision
%A Lu, Chia-Wen
%A Yang, Ching-Wen
%A Ma, Wei-Yun
%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 lu-etal-2024-automatic-construction
%X Aspect Sentiment Triplet Extraction (ASTE), introduced in 2020, is a task that involves the extraction of three key elements: target aspects, descriptive opinion spans, and their corresponding sentiment polarity. This process, however, faces a significant hurdle, particularly when applied to Chinese languages, due to the lack of sufficient datasets for model training, largely attributable to the arduous manual labeling process. To address this issue, we present an innovative framework that facilitates the automatic construction of ASTE via Iterative Weak Supervision, negating the need for manual labeling, aided by a discriminator to weed out subpar samples. The objective is to successively improve the quality of this raw data and generate supplementary data. The effectiveness of our approach is underscored by our results, which include the creation of a substantial Chinese review dataset. This dataset encompasses over 60,000 Google restaurant reviews in Chinese and features more than 200,000 extracted triplets. Moreover, we have also established a robust baseline model by leveraging a novel method of weak supervision. Both our dataset and model are openly accessible to the public.
%U https://aclanthology.org/2024.lrec-main.167
%P 1871-1882
Markdown (Informal)
[Automatic Construction of a Chinese Review Dataset for Aspect Sentiment Triplet Extraction via Iterative Weak Supervision](https://aclanthology.org/2024.lrec-main.167) (Lu et al., LREC-COLING 2024)
ACL