@inproceedings{wu-etal-2026-cmpa,
title = "{CMPA}-{SLU}: A Benchmark for {C}hinese Mobile Personal Assistant Spoken Language Understanding",
author = "Wu, Di and
Li, Zhongqiu and
Zhu, Zetao and
Xiong, Sishi and
Fang, Ruiyu and
Song, Shuangyong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2588/",
pages = "58811--58824",
ISBN = "979-8-89176-459-0",
abstract = "China has over 1.116 billion mobile Internet users, whose demands continue to evolve rapidly. However, existing Chinese spoken language understanding (SLU) benchmarks are outdated and cover limited domains, failing to reflect real-world mobile assistant scenarios. To this end, we introduce CMPA-SLU, a Chinese SLU dataset for mobile personal assistants collected from real-world applications and annotated with rigorous quality control. CMPA-SLU contains 50 domains, 247 intents, and 74 slot types, expanding the diversity of existing Chinese SLU benchmarks. To better simulate practical deployment scenarios, we further introduce a Partial Category setting, where candidate labels are dynamically filtered using a Bidirectional Guided Embedding (BGE)-based retrieval strategy. We further adopt a label mapping strategy for joint intent and slot prediction within a single generation process. We evaluate multiple large language models (LLMs) under both Full Category and Partial Category settings. Experimental results show that the Partial Category setting improves performance by reducing the candidate label space."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-cmpa">
<titleInfo>
<title>CMPA-SLU: A Benchmark for Chinese Mobile Personal Assistant Spoken Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongqiu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zetao</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sishi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiyu</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuangyong</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>China has over 1.116 billion mobile Internet users, whose demands continue to evolve rapidly. However, existing Chinese spoken language understanding (SLU) benchmarks are outdated and cover limited domains, failing to reflect real-world mobile assistant scenarios. To this end, we introduce CMPA-SLU, a Chinese SLU dataset for mobile personal assistants collected from real-world applications and annotated with rigorous quality control. CMPA-SLU contains 50 domains, 247 intents, and 74 slot types, expanding the diversity of existing Chinese SLU benchmarks. To better simulate practical deployment scenarios, we further introduce a Partial Category setting, where candidate labels are dynamically filtered using a Bidirectional Guided Embedding (BGE)-based retrieval strategy. We further adopt a label mapping strategy for joint intent and slot prediction within a single generation process. We evaluate multiple large language models (LLMs) under both Full Category and Partial Category settings. Experimental results show that the Partial Category setting improves performance by reducing the candidate label space.</abstract>
<identifier type="citekey">wu-etal-2026-cmpa</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2588/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>58811</start>
<end>58824</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CMPA-SLU: A Benchmark for Chinese Mobile Personal Assistant Spoken Language Understanding
%A Wu, Di
%A Li, Zhongqiu
%A Zhu, Zetao
%A Xiong, Sishi
%A Fang, Ruiyu
%A Song, Shuangyong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wu-etal-2026-cmpa
%X China has over 1.116 billion mobile Internet users, whose demands continue to evolve rapidly. However, existing Chinese spoken language understanding (SLU) benchmarks are outdated and cover limited domains, failing to reflect real-world mobile assistant scenarios. To this end, we introduce CMPA-SLU, a Chinese SLU dataset for mobile personal assistants collected from real-world applications and annotated with rigorous quality control. CMPA-SLU contains 50 domains, 247 intents, and 74 slot types, expanding the diversity of existing Chinese SLU benchmarks. To better simulate practical deployment scenarios, we further introduce a Partial Category setting, where candidate labels are dynamically filtered using a Bidirectional Guided Embedding (BGE)-based retrieval strategy. We further adopt a label mapping strategy for joint intent and slot prediction within a single generation process. We evaluate multiple large language models (LLMs) under both Full Category and Partial Category settings. Experimental results show that the Partial Category setting improves performance by reducing the candidate label space.
%U https://aclanthology.org/2026.emnlp-main.2588/
%P 58811-58824
Markdown (Informal)
[CMPA-SLU: A Benchmark for Chinese Mobile Personal Assistant Spoken Language Understanding](https://aclanthology.org/2026.emnlp-main.2588/) (Wu et al., EMNLP 2026)
ACL