Joint intent and slot recognition method via prompt-guided generation and tri-mutual attention

doi:10.11772/j.issn.1001-9081.2025091092

Journal of Computer Applications

Joint intent and slot recognition method via prompt-guided generation and tri-mutual attention

TENG Shangzhi¹，HUANG Jin¹，LYU Xueqiang¹，YOU Xindong²

1. Beijing Key Laboratory of Internet Culture Digital Dissemination, Beijing Information Science and Technology University 2. School of Information Engineering, Beijing Institute of Graphic Communication

Received:2025-09-18 Revised:2026-01-07 Online:2026-03-16 Published:2026-03-16
About author:TENG Shangzhi, born in 1989, Ph. D., associate professor. His research interests include natural language processing. HUANG Jin, born in 2000, M. S. candidate. His research interests include natural language processing. LYU Xueqiang, born in 1970, Ph. D., professor. His research interests include artificial intelligence, big data. YOU Xindong, born in 1989, Ph. D., professor. Her research interests include patent knowledge mining, natural language processing.
Supported by:
National Natural Science Foundation of China (62171043); Project of General Administration of Market Supervision and Quality of the People's Republic of China (0747-2461SCCZAE77)

基于提示引导生成与三元注意力的意图槽位联合识别方法

滕尚志¹,黄进¹,吕学强¹,游新冬²

1.北京信息科技大学网络文化与数字传播北京市重点实验室 2.北京印刷学院信息工程学院

通讯作者: 游新冬
作者简介:滕尚志(1989—)，男，江苏沛县人，副教授，博士，主要研究方向：自然语言处理；黄进(2000—)，男，河北唐山人，硕士研究生，主要研究方向：自然语言处理；吕学强(1970—)，男，辽宁抚顺人，教授，博士，CCF会员，主要研究方向：人工智能、大数据；游新冬(1989—)，女，福建永定人，教授，博士，主要研究方向：专利知识挖掘、自然语言处理。
基金资助:
国家自然科学基金资助项目（62171043）；国家市场质量监督管理总局项目（0747-2461SCCZAE77）

Abstract

Abstract: To address the semantic ambiguity and difficulty in candidate selection caused by the diverse results generated by large language models in intent recognition and slot filling tasks, a new approach for joint intent-slot recognition based on prompt-guided generation and tri-mutual attention was proposed，named PGT-Joint(Prompt-guided Generation and Tri-mutual Attention for Joint Intent–Slot Recognition). This approach first constructs prompts based on domain knowledge to guide the large language model in generating multiple candidate intent-slot combinations. Secondly, a tri-mutual attention mechanism is designed to explicitly model the high-order semantic relationships between user questions, candidate intents, and slots. Finally, a comparative learning-to-rank model is used to filter and optimize the candidate results. Experimental results on a Mini/Micro LED domain question-answering dataset show that, compared with baseline models such as BERT-Intent and BERT-Slot, PGT-Joint improves intent recognition accuracy by 0.4 to 3.8 percentage points and slot filling F1 score by 4.1 to 6.6 percentage points. Notably, the most significant gain is observed in joint matching accuracy, with an improvement of 5.2 to 10.2 percentage points. In addition, ablation experiments verified the key role of prompt generation and ternary interactive attention mechanism in performance improvement, indicating that PGT-Joint can effectively enhance semantic understanding capabilities in professional domain dialogue systems.

Key words: intent detection, slot filling, large language model, contrastive learning, attention mechanism

摘要： 针对大语言模型在意图识别与槽位填充任务中生成结果多样性带来的语义歧义和候选选择困难问题，提出了一种基于提示引导生成与三元交互注意力机制的意图-槽位联合识别方法，简称PGT-Joint(Prompt-guided Generation and Tri-mutual Attention for Joint intent–slot recognition)。该方法首先结合领域知识构建提示，引导大语言模型生成多组候选意图-槽位组合；其次设计三元交互注意力机制，显式建模用户问题、候选意图和槽位之间的高阶语义关系；最后通过对比学习排序模型对候选结果进行筛选与优化。实验结果表明，在Mini/Micro LED领域问答数据集上，与BERT-Intent、BERT-Slot等模型相比，PGT-Joint在意图识别准确率的提升幅度达到0.4~3.8个百分点，在槽位填充F1值的提升幅度达到4.1~6.6个百分点，在联合匹配准确率上的提升最为显著，提升幅度达到5.2~10.2个百分点。此外，消融实验验证了提示生成和三元交互注意力机制在性能提升中的关键作用，说明PGT-Joint能够在专业领域对话系统中有效增强语义理解能力。

关键词: 意图识别, 槽位填充, 大语言模型, 对比学习, 注意力机制

CLC Number:

TP391

TENG Shangzhi, HUANG Jin, LYU Xueqiang, YOU Xindong. Joint intent and slot recognition method via prompt-guided generation and tri-mutual attention[J]. Journal of Computer Applications, DOI: 10.11772/j.issn.1001-9081.2025091092.

滕尚志黄进吕学强游新冬. 基于提示引导生成与三元注意力的意图槽位联合识别方法[J]. 《计算机应用》唯一官方网站, DOI: 10.11772/j.issn.1001-9081.2025091092.

[1]	Haoyang ZHANG, Liping ZHANG, Sheng YAN, Na LI, Xuefei ZHANG. Review of large language model methods for knowledge graph completion [J]. Journal of Computer Applications, 2026, 46(3): 683-695.
[2]	Xiaoxia LIU, Liqun KUANG, Song WANG, Shichao JIAO, Huiyan HAN, Fengguang XIONG. Multi-scale spatio-temporal decoupling for contrastive learning of skeleton action recognition [J]. Journal of Computer Applications, 2026, 46(3): 767-774.
[3]	Bin SHEN, Xiaoning CHEN, Hua CHENG, Yiquan FANG, Huifeng WANG. Intelligent undergraduate teaching evaluation system based on large language models [J]. Journal of Computer Applications, 2026, 46(3): 993-1003.
[4]	Enkang XI, Jing FAN, Yadong JIN, Hua DONG, Hao YU, Yihang SUN. Review of threats faced by federated learning in privacy and security field [J]. Journal of Computer Applications, 2026, 46(3): 798-808.
[5]	Yiming HUANG, Xihua ZOU, Guo DENG, Di ZHENG. Pre-answering and retrieval filtering： dual-stage optimization method for RAG-based question-answering systems [J]. Journal of Computer Applications, 2026, 46(3): 696-707.
[6]	Yuhang XIAO, Guanfeng LI, Yuyin CHEN, Jing QIN. Few-shot relation extraction model with graph-based multi-view contrastive learning [J]. Journal of Computer Applications, 2026, 46(3): 732-740.
[7]	Dingjia WU, Zhe CUI. MG-SQL： SQL generation framework with enhanced schema linking and multi-generator collaboration [J]. Journal of Computer Applications, 2026, 46(3): 723-731.
[8]	Peirong SHAO, Suzhen LIN, Yanbo WANG. Human-centric detail-enhanced virtual try-on method [J]. Journal of Computer Applications, 2026, 46(3): 915-923.
[9]	Rilong WANG, Zhenping LI, Xiaosong LI, Qiang GAO, Ya HE, Yong ZHONG, Yingxiao ZHAO. Multi-Agent collaborative knowledge reasoning framework [J]. Journal of Computer Applications, 2026, 46(3): 708-714.
[10]	Zuxi ZHANG, Zhancheng ZHANG, Fuyuan HU. Local and long-range temporal complementary modeling for video action recognition [J]. Journal of Computer Applications, 2026, 46(3): 758-766.
[11]	Ming LI, Mengqi WANG, Aili ZHANG, Hua REN, Yuqiang DOU. Image steganography method based on conditional generative adversarial networks and hybrid attention mechanism [J]. Journal of Computer Applications, 2026, 46(2): 475-484.
[12]	Sizhong ZHANG, Jianyang LIU, Linfeng LI. Action quality assessment model based on trajectory-guided perceptual learning with X3D [J]. Journal of Computer Applications, 2026, 46(2): 555-563.
[13]	Rifeng ZHANG, Guangming LI, Yurong OUYANG. Low-light image enhancement network guided by reflection prior map [J]. Journal of Computer Applications, 2026, 46(2): 546-554.
[14]	Qianhui XU, Ke NIU, Shunzhe ZHU, Lin SHI, Jun LI. GAB3D-SEVSN： enhanced video steganography model via invertible neural network [J]. Journal of Computer Applications, 2026, 46(2): 467-474.
[15]	Junrui WU, Jiangchuan YANG, Haisheng YU, Sai ZOU, Wenyong WANG. Performance evaluation method for deterministic networks based on complex-enhanced attention graph neural network [J]. Journal of Computer Applications, 2026, 46(2): 505-517.

Joint intent and slot recognition method via prompt-guided generation and tri-mutual attention

基于提示引导生成与三元注意力的意图槽位联合识别方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics