{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T02:38:07Z","timestamp":1755225487656,"version":"3.43.0"},"reference-count":45,"publisher":"Emerald","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,15]]},"abstract":"<jats:sec>\n                  <jats:title>Purpose<\/jats:title>\n                  <jats:p>In the construction of task-oriented dialogue systems, collecting data in specific domains is difficult. This has made the automatic generation of a large amount of dialogue data a highly promising research direction. Traditional methods lack sufficient information diversity, which consequently leads to poor quality of generated dialogues and insufficient annotation accuracy. The purpose of this paper is to propose methods to generate higher-quality dialogues with more accurate annotations under few-shot conditions.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Design\/methodology\/approach<\/jats:title>\n                  <jats:p>This paper puts forward a dialogue retriever specifically designed for task-oriented dialogue generation. This retriever conducts retrieval based on two retrieval methods, namely, those based on user utterances and system responses. It screens out the training prompts that have a higher degree of fit with the test prompts as examples, thereby strengthening the in-context learning ability of large language models and effectively improving the quality of generated user utterances and system responses. Moreover, this paper proposes an automatic annotation correction mechanism, which overcomes the uncertainty of large language models and enhances the accuracy of annotations. This method requires almost no human involvement and can quickly generate dialogues at minimal cost.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Findings<\/jats:title>\n                  <jats:p>This paper conducts experiments on two data sets. The results show that compared with previous methods, under the condition of few samples, the method proposed in this paper can generate dialogues with better quality and more accurate annotations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Originality\/value<\/jats:title>\n                  <jats:p>In this research, this paper has proposed a turn-based dialogue retriever based on user utterances and system responses and designed a new similarity calculation method, as well as an automatic annotation correction mechanism for task-oriented dialogue generation. The calculation results have demonstrated the effectiveness of this method.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1108\/ijwis-01-2025-0007","type":"journal-article","created":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T23:32:29Z","timestamp":1745278349000},"page":"254-274","source":"Crossref","is-referenced-by-count":0,"title":["Few-shot task-oriented dialogue generation with in-context learning"],"prefix":"10.1108","volume":"21","author":[{"given":"Zhongqin","family":"Bi","sequence":"first","affiliation":[{"name":"Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,","place":["China"]}]},{"given":"Xueni","family":"Hu","sequence":"additional","affiliation":[{"name":"Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,","place":["China"]}]},{"given":"Weina","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,","place":["China"]}]},{"given":"Xiaoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,","place":["China"]}]}],"member":"140","published-online":{"date-parts":[[2025,4,23]]},"reference":[{"key":"2025081308465749000_ref001","doi-asserted-by":"crossref","unstructured":"Asri, L., He, J. and Suleman, K. (2016), \u201cA sequence-to-sequence model for user simulation in spoken dialogue systems\u201d, available at: https:\/\/arxiv.org\/abs\/1607.00070","DOI":"10.21437\/Interspeech.2016-1175"},{"issue":"3","key":"2025081308465749000_ref002","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1108\/IJWIS-12-2023-0249","article-title":"Chain-of-event prompting for multi-document summarization by large language models","volume":"20","author":"Bao","year":"2024","journal-title":"International Journal of Web Information Systems"},{"article-title":"Language models are few-shot learners","year":"2020","author":"Brown","key":"2025081308465749000_ref003"},{"key":"2025081308465749000_ref004","doi-asserted-by":"publisher","first-page":"a25","DOI":"10.1145\/3166054.3166058","article-title":"A survey on dialogue systems: recent advances and new frontiers","volume":"19","author":"Chen","year":"2017","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"2025081308465749000_ref005","doi-asserted-by":"crossref","unstructured":"Crook, P. and Marin, A. (2017), \u201cSequence to sequence modeling for user simulation in dialog systems\u201d, available at: https:\/\/api.semanticscholar.org\/CorpusID:10224712","DOI":"10.21437\/Interspeech.2017-161"},{"key":"2025081308465749000_ref006","unstructured":"Dong, Q., Li, L., Dai, D., Zheng, C., Wu, Z., Chang, B., Sun, X., Xu, J., Li, L. and Sui, Z. (2023), \u201cA survey for In-context learning\u201d, available at: https:\/\/api.semanticscholar.org\/CorpusID:263886074"},{"article-title":"MultiWOZ2.1: a consolidated multi-domain dialogue dataset with state corrections and state tracking baselines","year":"2020","author":"Eric","key":"2025081308465749000_ref01400"},{"key":"2025081308465749000_ref007","doi-asserted-by":"crossref","unstructured":"Gur, I., Hakkani-Tur, D., Tur, G. and Shah, P. (2018), \u201cUser modeling for task oriented dialogues\u201d, available at: https:\/\/arxiv.org\/abs\/1811.04369","DOI":"10.1109\/SLT.2018.8639652"},{"key":"2025081308465749000_ref008","doi-asserted-by":"crossref","unstructured":"Han, T., Liu, X., Takanobu, R., Lian, Y., Huang, C., Wan, D., Peng, W. and Huang, M. (2020), \u201cMultiWOZ 2.3: a multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation\u201d, available at: https:\/\/github.com\/lexmen318\/MultiWOZ-coref","DOI":"10.1007\/978-3-030-88483-3_16"},{"key":"2025081308465749000_ref01800","unstructured":"Hosseini-Asl, E., McCann, B., Wu, C.-S., Yavuz, S. and Socher, R. (2020), \u201cA simple language model for task-oriented dialogue\u201d, available at: https:\/\/arxiv.org\/abs\/2005.00796"},{"key":"2025081308465749000_ref009","doi-asserted-by":"publisher","first-page":"2627","DOI":"10.18653\/v1\/2022.findings-emnlp.193","article-title":"In-context learning for few-shot dialogue state tracking","author":"Hu","year":"2022"},{"issue":"3","key":"2025081308465749000_ref010","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3383123","article-title":"Challenges in building intelligent open-domain dialog systems","volume":"38","author":"Huang","year":"2020","journal-title":"ACM Transactions on Information Systems"},{"key":"2025081308465749000_ref01100","doi-asserted-by":"publisher","first-page":"6769","DOI":"10.18653\/v1\/2020.emnlp-main.550","article-title":"Dense passage retrieval for open-domain question answering","author":"Karpukhin","year":"2020"},{"key":"2025081308465749000_ref011","doi-asserted-by":"publisher","first-page":"53","DOI":"10.18653\/v1\/2022.sigdial-1.5","article-title":"Controllable user dialogue act augmentation for dialogue state tracking","author":"Lai","year":"2022"},{"key":"2025081308465749000_ref012","first-page":"119","article-title":"Wizard of Oz studies in HRI","volume":"1","author":"Laurel","year":"2012","journal-title":"Journal of Human-Robot Interaction"},{"key":"2025081308465749000_ref013","doi-asserted-by":"publisher","first-page":"4937","DOI":"10.18653\/v1\/2021.emnlp-main.404","article-title":"Dialogue state tracking with a language model using schema-driven prompting","author":"Lee","year":"2021"},{"key":"2025081308465749000_ref014","first-page":"4330","article-title":"Controllable dialogue simulation with in-context learning","author":"Li","year":"2022"},{"key":"2025081308465749000_ref01500","unstructured":"Li, M., Gong, S., Feng, J., Xu, Y., Zhang, J., Wu, Z. and Kong, L. (2023), \u201cIn-context learning with many demonstration examples\u201d, available at: https:\/\/arxiv.org\/abs\/2302.04931"},{"key":"2025081308465749000_ref015","unstructured":"Lin, Y., Zhong, B., Jiang, S. and Chen, J. (2024), \u201cReasoning graph enhanced exemplars retrieval for In-Context learning\u201d, available at: https:\/\/arxiv.org\/abs\/2409.11147"},{"key":"2025081308465749000_ref016","first-page":"3391","article-title":"Minimalist transfer learning for task-oriented dialogue systems","author":"Lin","year":"2018"},{"key":"2025081308465749000_ref017","first-page":"4581","article-title":"Latent attention for If-Then program synthesis","author":"Liu","year":"2016"},{"key":"2025081308465749000_ref018","first-page":"962","article-title":"ProphetChat: enhancing dialogue generation with simulation of future conversation","author":"Liu","year":"2022"},{"key":"2025081308465749000_ref019","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L. and Stoyanov, V. (2019), \u201cRoBERTa: a robustly optimized BERT pretraining approach\u201d, available at: https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"2025081308465749000_ref020","unstructured":"Poesia, G., Polozov, O., Le, V., Tiwari, A., Soares, G., Meek, C. and Gulwani, S. (2022), \u201cSynchromesh: reliable code generation from pre-trained language models\u201d, available at: https:\/\/arxiv.org\/abs\/2201.11227"},{"key":"2025081308465749000_ref04400","first-page":"5925","article-title":"End-to-end task-oriented dialogue: a survey of tasks, methods, and future directions","author":"Qin","year":"2023"},{"key":"2025081308465749000_ref09400","doi-asserted-by":"publisher","first-page":"3982","DOI":"10.18653\/v1\/D19-1410","article-title":"Sentence-BERT: sentence embeddings using Siamese BERT-Networks","author":"Reimers","year":"2019"},{"key":"2025081308465749000_ref08400","doi-asserted-by":"publisher","first-page":"2655","DOI":"10.18653\/v1\/2022.naacl-main.191","article-title":"Learning to retrieve prompts for in-context learning","author":"Rubin","year":"2022"},{"key":"2025081308465749000_ref021","doi-asserted-by":"publisher","first-page":"41","DOI":"10.18653\/v1\/n18-3006","article-title":"Bootstrapping a neural conversational agent with dialogue self-play, crowdsourcing and on-line reinforcement learning","volume":"3","author":"Shah","year":"2018","journal-title":"Human Language"},{"key":"2025081308465749000_ref022","first-page":"6566","article-title":"Dual-feedback knowledge retrieval for task-oriented dialogue systems","author":"Shi","year":"2023"},{"article-title":"GPTNeo: large scale autoregressive language modeling with mesh-tensorflow","year":"2021","author":"Sid","key":"2025081308465749000_ref07500"},{"key":"2025081308465749000_ref023","doi-asserted-by":"publisher","first-page":"4661","DOI":"10.18653\/v1\/2022.acl-long.319","article-title":"Multi-task pre-training for plug-and-play task-oriented dialogue system","author":"Su","year":"2022"},{"article-title":"CommonsenseQA 2.0: exposing the limits of {AI} through gamification","year":"2022","author":"Talmor","key":"2025081308465749000_ref02500"},{"key":"2025081308465749000_ref024","doi-asserted-by":"publisher","first-page":"917","DOI":"10.18653\/v1\/2020.emnlp-main.66","article-title":"TOD-BERT: pre-trained natural language understanding for task-oriented dialogue","author":"Wu","year":"2020"},{"issue":"4","key":"2025081308465749000_ref025","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1108\/IJWIS-12-2023-0256","article-title":"Large language models for automated Q&A involving legal documents: a survey on algorithms, frameworks and applications","volume":"20","author":"Yang","year":"2024","journal-title":"International Journal of Web Information Systems"},{"key":"2025081308465749000_ref026","doi-asserted-by":"publisher","first-page":"734","DOI":"10.18653\/v1\/2021.naacl-main.59","article-title":"Few-shot intent classification and slot filling with retrieved examples","author":"Yu","year":"2021"},{"issue":"10","key":"2025081308465749000_ref027","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1007\/s11431-020-1692-3","article-title":"Recent advances and challenges in task-oriented dialog systems","volume":"63","author":"Zhang","year":"2020","journal-title":"Science China Technological Sciences"},{"key":"2025081308465749000_ref028","unstructured":"Alon, T., Ori, Y., Ronan, L., Chandra, B., Yoav, G., Yejin, C. and Jonathan, B. (2022), \u201cCommonsenseQA 2.0: exposing the limits of {AI} through gamification\u201d, available at: https:\/\/arxiv.org\/abs\/2201.05320"},{"key":"2025081308465749000_ref029","unstructured":"Black, S., Gao, L., Wang, P., Leahy, C. and Biderman, S. (2021), \u201cGPT-Neo: large scale autoregressive language modeling with mesh-Tensorflow\u201d, available at: https:\/\/api.semanticscholar.org\/CorpusID:245758737"},{"key":"2025081308465749000_ref030","unstructured":"Ehsan, H., Bryan, M., ChienSheng, W., Semih, Y. and Richard, S. (2020), \u201cA simple language model for task-oriented dialogue\u201d, CoRR, available at: https:\/\/arxiv.org\/abs\/2005.00796"},{"key":"2025081308465749000_ref031","first-page":"5925","article-title":"End-to-end task-oriented dialogue: a survey of tasks, methods, and future directions","author":"Libo","year":"2023"},{"key":"2025081308465749000_ref032","unstructured":"Mihail, E., Rahul, G., Shachi, P., Abhishek, S., Sanchit, A., Shuyang, G., Adarsh, K., Anuj, G., Peter, K. and Dilek, H.T. (2020), \u201cMultiWOZ 2.1: a consolidated multi-domain dialogue dataset with state corrections and state tracking baselines\u201d, available at: https:\/\/github.com\/qbxlvnf11\/MultiWOZ2.1-parser"},{"key":"2025081308465749000_ref033","unstructured":"Mukai, L., Shansan, G., Jiangtao, F., Yiheng, X., Jun, Z., Zhiyong, W. and Lingpeng, K. (2023), \u201cIn-context learning with many demonstration examples\u201d, available at: https:\/\/arxiv.org\/abs\/2302.04931"},{"key":"2025081308465749000_ref034","doi-asserted-by":"publisher","first-page":"3982","DOI":"10.18653\/v1\/D19-1410","article-title":"Sentence-BERT: sentence embeddings using Siamese BERT-Networks","author":"Nils","year":"2019"},{"key":"2025081308465749000_ref035","doi-asserted-by":"publisher","first-page":"2655","DOI":"10.18653\/v1\/2022.naacl-main.191","article-title":"Learning to retrieve prompts for in-context learning","author":"Ohad","year":"2022"},{"key":"2025081308465749000_ref036","doi-asserted-by":"publisher","first-page":"6769","DOI":"10.18653\/v1\/2020.emnlp-main.550","article-title":"Dense passage retrieval for open-domain question answering","author":"Vladimir","year":"2020"}],"container-title":["International Journal of Web Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJWIS-01-2025-0007\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/ijwis\/article-pdf\/21\/3\/254\/10063596\/ijwis-01-2025-0007.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ijwis\/article-pdf\/21\/3\/254\/10063596\/ijwis-01-2025-0007.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T12:47:06Z","timestamp":1755089226000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ijwis\/article\/21\/3\/254\/1273627\/Few-shot-task-oriented-dialogue-generation-with-in"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,23]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5,15]]}},"URL":"https:\/\/doi.org\/10.1108\/ijwis-01-2025-0007","relation":{},"ISSN":["1744-0084","1744-0092"],"issn-type":[{"type":"print","value":"1744-0084"},{"type":"electronic","value":"1744-0092"}],"subject":[],"published":{"date-parts":[[2025,4,23]]}}}