@inproceedings{zhong-etal-2024-said,
title = "Who Said What: Formalization and Benchmarks for the Task of Quote Attribution",
author = "Zhong, Wenjie and
Naradowsky, Jason and
Takamura, Hiroya and
Kobayashi, Ichiro and
Miyao, Yusuke",
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.1530/",
pages = "17588--17602",
abstract = "The task of quote attribution seeks to pair textual utterances with the name of their speakers. Despite continuing research efforts on the task, models are rarely evaluated systematically against previous models in comparable settings on the same datasets. This has resulted in a poor understanding of the relative strengths and weaknesses of various approaches. In this work we formalize the task of quote attribution, and in doing so, establish a basis of comparison across existing models. We present an exhaustive benchmark of known models, including natural extensions to larger LLM base models, on all available datasets in both English and Chinese. Our benchmarking results reveal that the CEQA model attains state-of-the-art performance among all supervised methods, and ChatGPT, operating in a four-shot setting, demonstrates performance on par with or surpassing that of supervised methods on some datasets. Detailed error analysis identify several key factors contributing to prediction errors."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhong-etal-2024-said">
<titleInfo>
<title>Who Said What: Formalization and Benchmarks for the Task of Quote Attribution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Naradowsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ichiro</namePart>
<namePart type="family">Kobayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</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>The task of quote attribution seeks to pair textual utterances with the name of their speakers. Despite continuing research efforts on the task, models are rarely evaluated systematically against previous models in comparable settings on the same datasets. This has resulted in a poor understanding of the relative strengths and weaknesses of various approaches. In this work we formalize the task of quote attribution, and in doing so, establish a basis of comparison across existing models. We present an exhaustive benchmark of known models, including natural extensions to larger LLM base models, on all available datasets in both English and Chinese. Our benchmarking results reveal that the CEQA model attains state-of-the-art performance among all supervised methods, and ChatGPT, operating in a four-shot setting, demonstrates performance on par with or surpassing that of supervised methods on some datasets. Detailed error analysis identify several key factors contributing to prediction errors.</abstract>
<identifier type="citekey">zhong-etal-2024-said</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1530/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>17588</start>
<end>17602</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Who Said What: Formalization and Benchmarks for the Task of Quote Attribution
%A Zhong, Wenjie
%A Naradowsky, Jason
%A Takamura, Hiroya
%A Kobayashi, Ichiro
%A Miyao, Yusuke
%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 zhong-etal-2024-said
%X The task of quote attribution seeks to pair textual utterances with the name of their speakers. Despite continuing research efforts on the task, models are rarely evaluated systematically against previous models in comparable settings on the same datasets. This has resulted in a poor understanding of the relative strengths and weaknesses of various approaches. In this work we formalize the task of quote attribution, and in doing so, establish a basis of comparison across existing models. We present an exhaustive benchmark of known models, including natural extensions to larger LLM base models, on all available datasets in both English and Chinese. Our benchmarking results reveal that the CEQA model attains state-of-the-art performance among all supervised methods, and ChatGPT, operating in a four-shot setting, demonstrates performance on par with or surpassing that of supervised methods on some datasets. Detailed error analysis identify several key factors contributing to prediction errors.
%U https://aclanthology.org/2024.lrec-main.1530/
%P 17588-17602
Markdown (Informal)
[Who Said What: Formalization and Benchmarks for the Task of Quote Attribution](https://aclanthology.org/2024.lrec-main.1530/) (Zhong et al., LREC-COLING 2024)
ACL