@inproceedings{jo-etal-2024-untold-story,
title = "An Untold Story of Preprocessing Task Evaluation: An Alignment-based Joint Evaluation Approach",
author = "Jo, Eunkyul Leah and
Park, Angela Yoonseo and
Zhang, Grace Tianjiao and
Wang, Izia Xiaoxiao and
Wang, Junrui and
Mao, MingJia and
Park, Jungyeul",
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.119",
pages = "1327--1338",
abstract = "A preprocessing task such as tokenization and sentence boundary detection (SBD) has commonly been considered as NLP challenges that have already been solved. This perception is due to their generally good performance and the presence of pre-tokenized data. However, it{'}s important to note that the low error rates of current methods are mainly specific to certain tasks, and rule-based tokenization can be difficult to use across different systems. Despite being subtle, these limitations are significant in the context of the NLP pipeline. In this paper, we introduce a novel evaluation algorithm for the preprocessing task, including both tokenization and SBD results. This algorithm aims to enhance the reliability of evaluations by reevaluating the counts of true positive cases for F1 measures in both preprocessing tasks jointly. It achieves this through an alignment-based approach inspired by sentence and word alignments used in machine translation. Our evaluation algorithm not only allows for precise counting of true positive tokens and sentence boundaries but also combines these two evaluation tasks into a single organized pipeline. To illustrate and clarify the intricacies of this calculation and integration, we provide detailed pseudo-code configurations for implementation. Additionally, we offer empirical evidence demonstrating how sentence and word alignment can improve evaluation reliability and present case studies to further support our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jo-etal-2024-untold-story">
<titleInfo>
<title>An Untold Story of Preprocessing Task Evaluation: An Alignment-based Joint Evaluation Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eunkyul</namePart>
<namePart type="given">Leah</namePart>
<namePart type="family">Jo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="given">Yoonseo</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grace</namePart>
<namePart type="given">Tianjiao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Izia</namePart>
<namePart type="given">Xiaoxiao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junrui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">MingJia</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungyeul</namePart>
<namePart type="family">Park</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>A preprocessing task such as tokenization and sentence boundary detection (SBD) has commonly been considered as NLP challenges that have already been solved. This perception is due to their generally good performance and the presence of pre-tokenized data. However, it’s important to note that the low error rates of current methods are mainly specific to certain tasks, and rule-based tokenization can be difficult to use across different systems. Despite being subtle, these limitations are significant in the context of the NLP pipeline. In this paper, we introduce a novel evaluation algorithm for the preprocessing task, including both tokenization and SBD results. This algorithm aims to enhance the reliability of evaluations by reevaluating the counts of true positive cases for F1 measures in both preprocessing tasks jointly. It achieves this through an alignment-based approach inspired by sentence and word alignments used in machine translation. Our evaluation algorithm not only allows for precise counting of true positive tokens and sentence boundaries but also combines these two evaluation tasks into a single organized pipeline. To illustrate and clarify the intricacies of this calculation and integration, we provide detailed pseudo-code configurations for implementation. Additionally, we offer empirical evidence demonstrating how sentence and word alignment can improve evaluation reliability and present case studies to further support our approach.</abstract>
<identifier type="citekey">jo-etal-2024-untold-story</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.119</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1327</start>
<end>1338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Untold Story of Preprocessing Task Evaluation: An Alignment-based Joint Evaluation Approach
%A Jo, Eunkyul Leah
%A Park, Angela Yoonseo
%A Zhang, Grace Tianjiao
%A Wang, Izia Xiaoxiao
%A Wang, Junrui
%A Mao, MingJia
%A Park, Jungyeul
%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 jo-etal-2024-untold-story
%X A preprocessing task such as tokenization and sentence boundary detection (SBD) has commonly been considered as NLP challenges that have already been solved. This perception is due to their generally good performance and the presence of pre-tokenized data. However, it’s important to note that the low error rates of current methods are mainly specific to certain tasks, and rule-based tokenization can be difficult to use across different systems. Despite being subtle, these limitations are significant in the context of the NLP pipeline. In this paper, we introduce a novel evaluation algorithm for the preprocessing task, including both tokenization and SBD results. This algorithm aims to enhance the reliability of evaluations by reevaluating the counts of true positive cases for F1 measures in both preprocessing tasks jointly. It achieves this through an alignment-based approach inspired by sentence and word alignments used in machine translation. Our evaluation algorithm not only allows for precise counting of true positive tokens and sentence boundaries but also combines these two evaluation tasks into a single organized pipeline. To illustrate and clarify the intricacies of this calculation and integration, we provide detailed pseudo-code configurations for implementation. Additionally, we offer empirical evidence demonstrating how sentence and word alignment can improve evaluation reliability and present case studies to further support our approach.
%U https://aclanthology.org/2024.lrec-main.119
%P 1327-1338
Markdown (Informal)
[An Untold Story of Preprocessing Task Evaluation: An Alignment-based Joint Evaluation Approach](https://aclanthology.org/2024.lrec-main.119) (Jo et al., LREC-COLING 2024)
ACL
- Eunkyul Leah Jo, Angela Yoonseo Park, Grace Tianjiao Zhang, Izia Xiaoxiao Wang, Junrui Wang, MingJia Mao, and Jungyeul Park. 2024. An Untold Story of Preprocessing Task Evaluation: An Alignment-based Joint Evaluation Approach. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1327–1338, Torino, Italia. ELRA and ICCL.