@inproceedings{ocampo-diaz-ouyang-2024-measuring,
title = "Measuring Cross-Text Cohesion for Segmentation Similarity Scoring",
author = "Ocampo Diaz, Gerardo and
Ouyang, Jessica",
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.971",
pages = "11138--11147",
abstract = "Text segmentation is the task of dividing a sequence of text elements (eg. words, sentences, or paragraphs) into meaningful chunks. Although exciting advances are being made in modern segmentation-based tasks, such as automatically generating podcast chapters, current segmentation similarity metrics share a critical weakness: they are content-agnostic. In this paper, we present a word-embedding-based metric of cross-textual cohesion based on the formal linguistic definition of cohesion and incorporate it into a new segmentation similarity metric, SED. Our similarity metric, SED, is capable of providing fine-grained segmentation similarity scoring for the 3 basic segmentation errors: transposition, insertion, and deletion, as well as mixtures of them, avoiding the limitations of traditional metrics. We discuss the benefits of SED and evaluate its alignment with human judgement for each of the 3 basic error types. We show that our metric aligns with human evaluations significantly more than traditional metrics. We briefly discuss future work, such as the integration of anaphora resolution into our cohesion-based metric, and make our code publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ocampo-diaz-ouyang-2024-measuring">
<titleInfo>
<title>Measuring Cross-Text Cohesion for Segmentation Similarity Scoring</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gerardo</namePart>
<namePart type="family">Ocampo Diaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessica</namePart>
<namePart type="family">Ouyang</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>Text segmentation is the task of dividing a sequence of text elements (eg. words, sentences, or paragraphs) into meaningful chunks. Although exciting advances are being made in modern segmentation-based tasks, such as automatically generating podcast chapters, current segmentation similarity metrics share a critical weakness: they are content-agnostic. In this paper, we present a word-embedding-based metric of cross-textual cohesion based on the formal linguistic definition of cohesion and incorporate it into a new segmentation similarity metric, SED. Our similarity metric, SED, is capable of providing fine-grained segmentation similarity scoring for the 3 basic segmentation errors: transposition, insertion, and deletion, as well as mixtures of them, avoiding the limitations of traditional metrics. We discuss the benefits of SED and evaluate its alignment with human judgement for each of the 3 basic error types. We show that our metric aligns with human evaluations significantly more than traditional metrics. We briefly discuss future work, such as the integration of anaphora resolution into our cohesion-based metric, and make our code publicly available.</abstract>
<identifier type="citekey">ocampo-diaz-ouyang-2024-measuring</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.971</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11138</start>
<end>11147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring Cross-Text Cohesion for Segmentation Similarity Scoring
%A Ocampo Diaz, Gerardo
%A Ouyang, Jessica
%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 ocampo-diaz-ouyang-2024-measuring
%X Text segmentation is the task of dividing a sequence of text elements (eg. words, sentences, or paragraphs) into meaningful chunks. Although exciting advances are being made in modern segmentation-based tasks, such as automatically generating podcast chapters, current segmentation similarity metrics share a critical weakness: they are content-agnostic. In this paper, we present a word-embedding-based metric of cross-textual cohesion based on the formal linguistic definition of cohesion and incorporate it into a new segmentation similarity metric, SED. Our similarity metric, SED, is capable of providing fine-grained segmentation similarity scoring for the 3 basic segmentation errors: transposition, insertion, and deletion, as well as mixtures of them, avoiding the limitations of traditional metrics. We discuss the benefits of SED and evaluate its alignment with human judgement for each of the 3 basic error types. We show that our metric aligns with human evaluations significantly more than traditional metrics. We briefly discuss future work, such as the integration of anaphora resolution into our cohesion-based metric, and make our code publicly available.
%U https://aclanthology.org/2024.lrec-main.971
%P 11138-11147
Markdown (Informal)
[Measuring Cross-Text Cohesion for Segmentation Similarity Scoring](https://aclanthology.org/2024.lrec-main.971) (Ocampo Diaz & Ouyang, LREC-COLING 2024)
ACL