@inproceedings{kim-etal-2025-kstc,
title = "{KSTC}: Keyphrase-driven Sentence embedding and Task independent prompting for filling slot in the Generation of theme label",
author = "Kim, Sua and
Jeong, Taeyoung and
Hong, Seokyoung and
Kim, Seongjun and
Lee, Jeongpil and
Chang, Du-Seong and
Koo, Myoung-Wan",
editor = "Hedayatnia, Behnam and
Chen, Vivian and
Chen, Zhang and
Gupta, Raghav and
Galley, Michel",
booktitle = "Proceedings of the Twelfth Dialog System Technology Challenge",
month = aug,
year = "2025",
address = "Avignon, France",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.dstc-1.5/",
pages = "44--73",
ISBN = "979-8-89176-330-2",
abstract = "Intent discovery in task-oriented dialogue is typically cast as single-turn intent classification, leaving systems brittle when user goals fall outside predefined inventories. We reformulate the task as multi-turn zero-shot intent discovery and present KSTC, a framework that (i) embeds dialogue contexts, (ii) performs coarse clustering, (iii) generates predicted theme label for each cluster, (iv) refines clusters using the Large Language Model (LLM) using predicted theme label, and (v) relocates utterances according to user{'}s preference. Because generating informative predicted theme label is crucial during the LLM-driven cluster refinement process, we propose the Task Independent Slots (TIS), which generates effective theme label by extracting verb and noun slot{--}value.Evaluated on DSTC12 Track2 dataset, KSTC took the first place, improving clustering and labeling quality without in-domain supervision. Results show that leveraging conversational context and slot-guided LLM labeling yields domain-agnostic theme clusters that remain consistent under distributional shift. KSTC thus offers a scalable, label-free solution for real-world dialogue systems that must continuously surface novel user intents. We will release our code and prompts publicly."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2025-kstc">
<titleInfo>
<title>KSTC: Keyphrase-driven Sentence embedding and Task independent prompting for filling slot in the Generation of theme label</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sua</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taeyoung</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokyoung</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seongjun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeongpil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Du-Seong</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Myoung-Wan</namePart>
<namePart type="family">Koo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Dialog System Technology Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Behnam</namePart>
<namePart type="family">Hedayatnia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghav</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Galley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Avignon, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-330-2</identifier>
</relatedItem>
<abstract>Intent discovery in task-oriented dialogue is typically cast as single-turn intent classification, leaving systems brittle when user goals fall outside predefined inventories. We reformulate the task as multi-turn zero-shot intent discovery and present KSTC, a framework that (i) embeds dialogue contexts, (ii) performs coarse clustering, (iii) generates predicted theme label for each cluster, (iv) refines clusters using the Large Language Model (LLM) using predicted theme label, and (v) relocates utterances according to user’s preference. Because generating informative predicted theme label is crucial during the LLM-driven cluster refinement process, we propose the Task Independent Slots (TIS), which generates effective theme label by extracting verb and noun slot–value.Evaluated on DSTC12 Track2 dataset, KSTC took the first place, improving clustering and labeling quality without in-domain supervision. Results show that leveraging conversational context and slot-guided LLM labeling yields domain-agnostic theme clusters that remain consistent under distributional shift. KSTC thus offers a scalable, label-free solution for real-world dialogue systems that must continuously surface novel user intents. We will release our code and prompts publicly.</abstract>
<identifier type="citekey">kim-etal-2025-kstc</identifier>
<location>
<url>https://aclanthology.org/2025.dstc-1.5/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>44</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KSTC: Keyphrase-driven Sentence embedding and Task independent prompting for filling slot in the Generation of theme label
%A Kim, Sua
%A Jeong, Taeyoung
%A Hong, Seokyoung
%A Kim, Seongjun
%A Lee, Jeongpil
%A Chang, Du-Seong
%A Koo, Myoung-Wan
%Y Hedayatnia, Behnam
%Y Chen, Vivian
%Y Chen, Zhang
%Y Gupta, Raghav
%Y Galley, Michel
%S Proceedings of the Twelfth Dialog System Technology Challenge
%D 2025
%8 August
%I Association for Computational Linguistics
%C Avignon, France
%@ 979-8-89176-330-2
%F kim-etal-2025-kstc
%X Intent discovery in task-oriented dialogue is typically cast as single-turn intent classification, leaving systems brittle when user goals fall outside predefined inventories. We reformulate the task as multi-turn zero-shot intent discovery and present KSTC, a framework that (i) embeds dialogue contexts, (ii) performs coarse clustering, (iii) generates predicted theme label for each cluster, (iv) refines clusters using the Large Language Model (LLM) using predicted theme label, and (v) relocates utterances according to user’s preference. Because generating informative predicted theme label is crucial during the LLM-driven cluster refinement process, we propose the Task Independent Slots (TIS), which generates effective theme label by extracting verb and noun slot–value.Evaluated on DSTC12 Track2 dataset, KSTC took the first place, improving clustering and labeling quality without in-domain supervision. Results show that leveraging conversational context and slot-guided LLM labeling yields domain-agnostic theme clusters that remain consistent under distributional shift. KSTC thus offers a scalable, label-free solution for real-world dialogue systems that must continuously surface novel user intents. We will release our code and prompts publicly.
%U https://aclanthology.org/2025.dstc-1.5/
%P 44-73
Markdown (Informal)
[KSTC: Keyphrase-driven Sentence embedding and Task independent prompting for filling slot in the Generation of theme label](https://aclanthology.org/2025.dstc-1.5/) (Kim et al., DSTC 2025)
ACL