{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:40:02Z","timestamp":1749998402630,"version":"3.41.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705519"},{"type":"electronic","value":"9783031705526"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70552-6_14","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"233-247","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Retrieval-Based Dialogue Systems: Fine-Grained Post-training Prompt Adaptation and\u00a0Pairwise Optimization Fine-Tuning Strategy"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4462-6091","authenticated-orcid":false,"given":"Tianqing","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5464-0594","authenticated-orcid":false,"given":"Alimjan","family":"Aysa","sequence":"additional","affiliation":[]},{"given":"Li","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9283-6549","authenticated-orcid":false,"given":"Kurban","family":"Ubul","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0029-2018","authenticated-orcid":false,"given":"Enguang","family":"Zuo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"14_CR1","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"14_CR2","unstructured":"Vig, J., Ramea, K.: Comparison of transfer-learning approaches for response selection in multi-turn conversations. In: Workshop on DSTC7 (2019)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Lu, J., et al.: Improving contextual language models for response retrieval in multi-turn conversation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1805\u20131808 (2020)","DOI":"10.1145\/3397271.3401255"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Gu, J.-C., et al.: Speaker-aware BERT for multi-turn response selection in retrieval-based chatbots. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 2041\u20132044 (2020)","DOI":"10.1145\/3340531.3412330"},{"issue":"10","key":"14_CR5","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2009)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"59","key":"14_CR6","first-page":"1","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(59), 1\u201335 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Han, X., Eisenstein, J.: Unsupervised domain adaptation of contextualized embeddings for sequence labeling. arXiv preprint arXiv:1904.02817 (2019)","DOI":"10.18653\/v1\/D19-1433"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Mehri, S., et al.: Pretraining methods for dialog context representation learning. arXiv preprint arXiv:1906.00414 (2019)","DOI":"10.18653\/v1\/P19-1373"},{"key":"14_CR9","unstructured":"Xu, H., et al.: BERT post-training for review reading comprehension and aspect-based sentiment analysis. arXiv preprint arXiv:1904.02232 (2019)"},{"issue":"9","key":"14_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu, P., et al.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9), 1\u201335 (2023)","journal-title":"ACM Comput. Surv."},{"key":"14_CR11","unstructured":"Asghar, N., et al.: Deep active learning for dialogue generation. arXiv preprint arXiv:1612.03929 (2016)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Bi, W., et al.: Fine-grained sentence functions for short-text conversation. arXiv preprint arXiv:1907.10302 (2019)","DOI":"10.18653\/v1\/P19-1389"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Sequential matching network: a new architecture for multiturn response selection in retrieval-based chatbots. arXiv preprint arXiv:1612.01627 (2016)","DOI":"10.18653\/v1\/P17-1046"},{"key":"14_CR14","unstructured":"Zhu, Q., et al.: Retrieval-enhanced adversarial training for neural response generation. arXiv preprint arXiv:1809.04276 (2018)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Tao, C., et al.: One time of interaction may not be enough: go deep with an interaction-over-interaction network for response selection in dialogues. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1\u201311 (2019)","DOI":"10.18653\/v1\/P19-1001"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: Multi-turn response selection for chatbots with deep attention matching network. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1118\u20131127 (2018)","DOI":"10.18653\/v1\/P18-1103"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Xu, R., et al.: Learning an effective context-response matching model with self-supervised tasks for retrieval-based dialogues. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 16, pp. 14158\u201314166 (2021)","DOI":"10.1609\/aaai.v35i16.17666"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Wu, W., et al.: Proactive human-machine conversation with explicit conversation goals. arXiv preprint arXiv:1906.05572 (2019)","DOI":"10.18653\/v1\/P19-1369"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Zhong, P., et al.: Towards persona-based empathetic conversational models. arXiv preprint arXiv:2004.12316 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.531"},{"key":"14_CR20","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/978-3-030-84186-7_31","volume-title":"Chinese Computational Linguistics","author":"Z Liu","year":"2021","unstructured":"Liu, Z., Lin, W., Shi, Y., Zhao, J.: A robustly optimized BERT pre-training approach with post-training. In: Li, S., et al. (eds.) CCL 2021. LNCS (LNAI), vol. 12869, pp. 471\u2013484. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-84186-7_31"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Whang, T., et al.: An effective domain adaptive post-training method for bert in response selection. arXiv preprint arXiv:1908.04812 (2019)","DOI":"10.21437\/Interspeech.2020-2153"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Han, J., et al.: Fine-grained post-training for improving retrieval based dialogue systems. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1549\u20131558 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.122"},{"key":"14_CR23","unstructured":"Mann, B., et al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Friedman, D., Chen, D.: Factual probing is [mask]: learning vs. learning to recall. arXiv preprint arXiv:2104.05240 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Wang, H., Xu, C., McAuley, J.: Automatic multi-label prompting: simple and interpretable few-shot classification. arXiv preprint arXiv:2204.06305 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.401"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Hu, S., et al.: Knowledgeable prompt-tuning: Incorporating knowledge into prompt verbalizer for text classification. arXiv preprint arXiv:2108.02035 (2021)","DOI":"10.18653\/v1\/2022.acl-long.158"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Shin, T., et al.: Autoprompt: eliciting knowledge from language models with automatically generated prompts. arXiv preprint arXiv:2010.15980 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Wu, H., Shi, X.: Adversarial soft prompt tuning for crossdomain sentiment analysis. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2438\u20132447 (2022)","DOI":"10.18653\/v1\/2022.acl-long.174"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Lowe, R., et al.: The ubuntu dialogue corpus: a large dataset for research in unstructured multi-turn dialogue systems. arXiv preprint arXiv:1506.08909 (2015)","DOI":"10.18653\/v1\/W15-4640"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Incorporating loose-structured knowledge into conversation modeling via recall-gate LSTM. In: 2017 International Joint Conference on Neural Networks (IJCNN) (2016)","DOI":"10.1109\/IJCNN.2017.7966297"},{"key":"14_CR31","unstructured":"Zhang, Z., et al.: Modeling multi-turn conversation with deep utterance aggregation. arXiv preprint arXiv:1806.09102 (2018)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Yuan, C., et al.: Multi-hop selector network for multi-turn response selection in retrieval-based chatbots. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLPIJCNLP), pp. 111\u2013120 (2019)","DOI":"10.18653\/v1\/D19-1011"},{"key":"14_CR33","unstructured":"Devlin, J., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Whang, T., et al.: Do response selection models really know what\u2019s next? Utterance manipulation strategies for multi-turn response selection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 16, pp. 14041\u201314049 (2021)","DOI":"10.1609\/aaai.v35i16.17653"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Song, C., et al.: Uni-encoder: a fast and accurate response selection paradigm for generation-based dialogue systems. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 6231\u20136244 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.388"},{"key":"14_CR36","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback (2022). https:\/\/arxiv.org\/abs\/2203.02155"},{"key":"14_CR37","unstructured":"Leike, J., et al.: Scalable agent alignment via reward modeling: a research direction. arXiv preprint arXiv:1811.07871 (2018)"},{"key":"14_CR38","unstructured":"Schulman, J., et al.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70552-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:07:30Z","timestamp":1749996450000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70552-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705519","9783031705526"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70552-6_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"11 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}