{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T14:45:59Z","timestamp":1777301159825,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792258","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:28:36Z","timestamp":1777296516000},"page":"99-110","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PMIScore: An Unsupervised Approach to Quantify Dialogue Engagement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2816-4149","authenticated-orcid":false,"given":"Yongkang","family":"Guo","sequence":"first","affiliation":[{"name":"CFCS, School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1825-8926","authenticated-orcid":false,"given":"Zhihuan","family":"Huang","sequence":"additional","affiliation":[{"name":"CFCS, School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5901-3004","authenticated-orcid":false,"given":"Yuqing","family":"Kong","sequence":"additional","affiliation":[{"name":"CFCS, School of Computer Science, Peking University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1966.tb00626.x"},{"key":"e_1_3_2_1_2_1","volume-title":"International conference on machine learning. PMLR, 531-540","author":"Belghazi Mohamed Ishmael","year":"2018","unstructured":"Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeshwar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, and Devon Hjelm. 2018. Mutual information neural estimation. In International conference on machine learning. PMLR, 531-540."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.137"},{"key":"e_1_3_2_1_4_1","volume-title":"Gptscore: Evaluate as you desire. arXiv preprint arXiv:2302.04166","author":"Fu Jinlan","year":"2023","unstructured":"Jinlan Fu, See-Kiong Ng, Zhengbao Jiang, and Pengfei Liu. 2023. Gptscore: Evaluate as you desire. arXiv preprint arXiv:2302.04166 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3079"},{"key":"e_1_3_2_1_6_1","volume-title":"Topic-based evaluation for conversational bots. arXiv preprint arXiv:1801.03622","author":"Guo Fenfei","year":"2018","unstructured":"Fenfei Guo, Angeliki Metallinou, Chandra Khatri, Anirudh Raju, Anu Venkatesh, and Ashwin Ram. 2018. Topic-based evaluation for conversational bots. arXiv preprint arXiv:1801.03622 (2018)."},{"key":"e_1_3_2_1_7_1","volume-title":"MINE: mutual information neural estimation. arXiv e-prints","author":"Belghazi Mohamed Ishmael","year":"2018","unstructured":"Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, and R Devon Hjelm. 2018. MINE: mutual information neural estimation. arXiv e-prints (2018), arXiv-1801."},{"key":"e_1_3_2_1_8_1","volume-title":"Scaling sentence embeddings with large language models. arXiv preprint arXiv:2307.16645","author":"Jiang Ting","year":"2023","unstructured":"Ting Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang, and Fuzhen Zhuang. 2023. Scaling sentence embeddings with large language models. arXiv preprint arXiv:2307.16645 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219166.3219194"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3296670"},{"key":"e_1_3_2_1_11_1","first-page":"986","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Asian Federation of Natural Language Processing","author":"Li Yanran","year":"2017","unstructured":"Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Asian Federation of Natural Language Processing, Taipei, Taiwan, 986-995. https:\/\/aclanthology.org\/I17-1099\/"},{"key":"e_1_3_2_1_12_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81."},{"key":"e_1_3_2_1_13_1","volume-title":"G-eval: NLG evaluation using gpt-4 with better human alignment. arXiv preprint arXiv:2303.16634","author":"Liu Yang","year":"2023","unstructured":"Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, and Chenguang Zhu. 2023. G-eval: NLG evaluation using gpt-4 with better human alignment. arXiv preprint arXiv:2303.16634 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"XuanLong Nguyen Martin J Wainwright and Michael I Jordan. 2009. On surrogate loss functions and f-divergences. (2009).","DOI":"10.1214\/08-AOS595"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068870"},{"key":"e_1_3_2_1_16_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_3_2_1_18_1","volume-title":"On estimation of a probability density function and mode. The annals of mathematical statistics","author":"Parzen Emanuel","year":"1962","unstructured":"Emanuel Parzen. 1962. On estimation of a probability density function and mode. The annals of mathematical statistics, Vol. 33, 3 (1962), 1065-1076."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1534"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.dialdoc-1.9"},{"key":"e_1_3_2_1_21_1","unstructured":"Ralph Tyrell Rockafellar. 2015. Convex analysis:(pms-28). (2015)."},{"key":"e_1_3_2_1_22_1","volume-title":"DSTC11: The Eleventh Dialog System Technology Challenge (24th Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)). Prague, Czechia.","author":"Rodr\u00edguez-Cantelar Mario","year":"2023","unstructured":"Mario Rodr\u00edguez-Cantelar, Chen Zhang, Chengguang Tang, Ke Shi, Sarik Ghazarian, Jo\u00e3o Sedoc, Luis Fernando D'Haro, and Alexander Rudnicky. 2023. Overview of Robust and Multilingual Automatic Evaluation Metrics for Open-Domain Dialogue Systems at DSTC 11 Track 4. In DSTC11: The Eleventh Dialog System Technology Challenge (24th Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)). Prague, Czechia."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.124"},{"key":"e_1_3_2_1_24_1","volume-title":"Learning and strongly truthful multi-task peer prediction: A variational approach. arXiv preprint arXiv:2009.14730","author":"Schoenebeck Grant","year":"2020","unstructured":"Grant Schoenebeck and Fang-Yi Yu. 2020. Learning and strongly truthful multi-task peer prediction: A variational approach. arXiv preprint arXiv:2009.14730 (2020)."},{"key":"e_1_3_2_1_25_1","volume-title":"What makes a good conversation? how controllable attributes affect human judgments. arXiv preprint arXiv:1902.08654","author":"Roller Stephen","year":"2019","unstructured":"Abigail See, Stephen Roller, Douwe Kiela, and Jason Weston. 2019. What makes a good conversation? how controllable attributes affect human judgments. arXiv preprint arXiv:1902.08654 (2019)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3364063"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60450-9_8"},{"key":"e_1_3_2_1_28_1","volume-title":"Benchmarking LLMs' Judgments with No Gold Standard. arXiv preprint arXiv:2411.07127","author":"Xu Shengwei","year":"2024","unstructured":"Shengwei Xu, Yuxuan Lu, Grant Schoenebeck, and Yuqing Kong. 2024. Benchmarking LLMs' Judgments with No Gold Standard. arXiv preprint arXiv:2411.07127 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Towards coherent and engaging spoken dialog response generation using automatic conversation evaluators. arXiv preprint arXiv:1904.13015","author":"Yi Sanghyun","year":"2019","unstructured":"Sanghyun Yi, Rahul Goel, Chandra Khatri, Alessandra Cervone, Tagyoung Chung, Behnam Hedayatnia, Anu Venkatesh, Raefer Gabriel, and Dilek Hakkani-Tur. 2019. Towards coherent and engaging spoken dialog response generation using automatic conversation evaluators. arXiv preprint arXiv:1904.13015 (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1205"},{"key":"e_1_3_2_1_31_1","volume-title":"Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675","author":"Zhang Tianyi","year":"2019","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)."},{"key":"e_1_3_2_1_32_1","volume-title":"DialogMI: A Dialogue Model Based on Enhancing Dialogue Mutual Information. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1-5.","author":"Zhang Yibo","year":"2023","unstructured":"Yibo Zhang, Ping Gong, Zelin Wang, Zhe Li, and Xuanyuan Yang. 2023. DialogMI: A Dialogue Model Based on Enhancing Dialogue Mutual Information. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1-5."},{"key":"e_1_3_2_1_33_1","volume-title":"Yongchan Kwon, and James Zou.","author":"Zheng Shuran","year":"2024","unstructured":"Shuran Zheng, Xuan Qi, Rui Ray Chen, Yongchan Kwon, and James Zou. 2024. Proper Dataset Valuation by Pointwise Mutual Information. arXiv preprint arXiv:2405.18253 (2024)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.635"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:56:05Z","timestamp":1777298165000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792258"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":34,"alternative-id":["10.1145\/3774904.3792258","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792258","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}