@inproceedings{yang-etal-2025-unified,
title = "A Unified Supervised and Unsupervised Dialogue Topic Segmentation Framework Based on Utterance Pair Modeling",
author = "Yang, Shihao and
Zhang, Ziyi and
Jiang, Yue and
Qin, Chunsheng and
Liu, Shuhua",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.252/",
doi = "10.18653/v1/2025.naacl-long.252",
pages = "4898--4908",
ISBN = "979-8-89176-189-6",
abstract = "The Dialogue Topic Segmentation task aims to divide a dialogue into different topic paragraphs in order to better understand the structure and content of the dialogue. Due to the short sentences, serious references and non-standard language in the dialogue, it is difficult to determine the boundaries of the topic. Although the unsupervised approaches based on LLMs performs well, it is still difficult to surpass the supervised methods based on classical models in specific domains. To this end, this paper proposes UPS (Utterance Pair Segment), a dialogue topic segmentation method based on utterance pair relationship modeling, unifying the supervised and unsupervised network architectures. For supervised pre-training, the model predicts the adjacency and topic affiliation of utterances in dialogues. For unsupervised pre-training, the dialogue-level and utterance-level relationship prediction tasks are used to train the model. The pre-training and fine-tuning strategies are carried out in different scenarios, such as supervised, few-shot, and unsupervised data. By adding a domain adapter and a task adapter to the Transformer, the model learns in the pre-training and fine-tuning stages, respectively, which significantly improves the segmentation effect. As the result, the proposed method has achieved the best results on multiple benchmark datasets across various scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2025-unified">
<titleInfo>
<title>A Unified Supervised and Unsupervised Dialogue Topic Segmentation Framework Based on Utterance Pair Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shihao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunsheng</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuhua</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>The Dialogue Topic Segmentation task aims to divide a dialogue into different topic paragraphs in order to better understand the structure and content of the dialogue. Due to the short sentences, serious references and non-standard language in the dialogue, it is difficult to determine the boundaries of the topic. Although the unsupervised approaches based on LLMs performs well, it is still difficult to surpass the supervised methods based on classical models in specific domains. To this end, this paper proposes UPS (Utterance Pair Segment), a dialogue topic segmentation method based on utterance pair relationship modeling, unifying the supervised and unsupervised network architectures. For supervised pre-training, the model predicts the adjacency and topic affiliation of utterances in dialogues. For unsupervised pre-training, the dialogue-level and utterance-level relationship prediction tasks are used to train the model. The pre-training and fine-tuning strategies are carried out in different scenarios, such as supervised, few-shot, and unsupervised data. By adding a domain adapter and a task adapter to the Transformer, the model learns in the pre-training and fine-tuning stages, respectively, which significantly improves the segmentation effect. As the result, the proposed method has achieved the best results on multiple benchmark datasets across various scenarios.</abstract>
<identifier type="citekey">yang-etal-2025-unified</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.252</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.252/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>4898</start>
<end>4908</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Unified Supervised and Unsupervised Dialogue Topic Segmentation Framework Based on Utterance Pair Modeling
%A Yang, Shihao
%A Zhang, Ziyi
%A Jiang, Yue
%A Qin, Chunsheng
%A Liu, Shuhua
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F yang-etal-2025-unified
%X The Dialogue Topic Segmentation task aims to divide a dialogue into different topic paragraphs in order to better understand the structure and content of the dialogue. Due to the short sentences, serious references and non-standard language in the dialogue, it is difficult to determine the boundaries of the topic. Although the unsupervised approaches based on LLMs performs well, it is still difficult to surpass the supervised methods based on classical models in specific domains. To this end, this paper proposes UPS (Utterance Pair Segment), a dialogue topic segmentation method based on utterance pair relationship modeling, unifying the supervised and unsupervised network architectures. For supervised pre-training, the model predicts the adjacency and topic affiliation of utterances in dialogues. For unsupervised pre-training, the dialogue-level and utterance-level relationship prediction tasks are used to train the model. The pre-training and fine-tuning strategies are carried out in different scenarios, such as supervised, few-shot, and unsupervised data. By adding a domain adapter and a task adapter to the Transformer, the model learns in the pre-training and fine-tuning stages, respectively, which significantly improves the segmentation effect. As the result, the proposed method has achieved the best results on multiple benchmark datasets across various scenarios.
%R 10.18653/v1/2025.naacl-long.252
%U https://aclanthology.org/2025.naacl-long.252/
%U https://doi.org/10.18653/v1/2025.naacl-long.252
%P 4898-4908
Markdown (Informal)
[A Unified Supervised and Unsupervised Dialogue Topic Segmentation Framework Based on Utterance Pair Modeling](https://aclanthology.org/2025.naacl-long.252/) (Yang et al., NAACL 2025)
ACL