{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:20:08Z","timestamp":1750220408775,"version":"3.41.0"},"reference-count":79,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T00:00:00Z","timestamp":1628726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2021,11,30]]},"abstract":"<jats:p>Learning to generate coherent and informative dialogs is an enduring challenge for open-domain conversation generation. Previous work leverage knowledge graph or documents to facilitate informative dialog generation, with little attention on dialog coherence. In this article, to enhance multi-turn open-domain dialog coherence, we propose to leverage a new knowledge source, web search session data, to facilitate hierarchical knowledge sequence planning, which determines a sketch of a multi-turn dialog. Specifically, we formulate knowledge sequence planning or dialog policy learning as a graph grounded Reinforcement Learning (RL) problem. To this end, we first build a two-level query graph with queries as utterance-level vertices and their topics (entities in queries) as topic-level vertices. We then present a two-level dialog policy model that plans a high-level topic sequence and a low-level query sequence over the query graph to guide a knowledge aware response generator. In particular, to foster forward-looking knowledge planning decisions for better dialog coherence, we devise a heterogeneous graph neural network to incorporate neighbouring vertex information, or possible future RL action information, into each vertex (as an RL action) representation. Experiment results on two benchmark dialog datasets demonstrate that our framework can outperform strong baselines in terms of dialog coherence, informativeness, and engagingness.<\/jats:p>","DOI":"10.1145\/3462551","type":"journal-article","created":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T16:57:58Z","timestamp":1628787478000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Coherent Dialog Generation with Query Graph"],"prefix":"10.1145","volume":"20","author":[{"given":"Jun","family":"Xu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, Heilongjiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyang","family":"Lei","sequence":"additional","affiliation":[{"name":"Baidu, Inc., Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haifeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu, Inc., Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng-Yu","family":"Niu","sequence":"additional","affiliation":[{"name":"Baidu, Inc., Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Wu","sequence":"additional","affiliation":[{"name":"Baidu, Inc., Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3907-0335","authenticated-orcid":false,"given":"Wanxiang","family":"Che","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, Heilongjiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1022-0309","authenticated-orcid":false,"given":"Jizhou","family":"Huang","sequence":"additional","affiliation":[{"name":"Baidu, Inc., Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, Heilongjiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,8,12]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Nabiha Asghar Pascal Poupart Jiang Xin and Hang Li. 2016. Online sequence-to-sequence reinforcement learning for open-domain conversational agents. arXiv:1612.039293. Retrieved from https:\/\/arxiv.org\/abs\/1612.039293.  Nabiha Asghar Pascal Poupart Jiang Xin and Hang Li. 2016. Online sequence-to-sequence reinforcement learning for open-domain conversational agents. arXiv:1612.039293. Retrieved from https:\/\/arxiv.org\/abs\/1612.039293."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3115\/1072133.1072149"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999923"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/3367722.3367729"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462272"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2919872"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6250"},{"volume-title":"Proceedings of the 27th International Conference on Computational Linguistics. 1257\u20131268","year":"2018","author":"Chen Lu","key":"e_1_2_1_8_1"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1189"},{"volume-title":"Proceedings of the International Conference on Learning Representations (ICLR'19)","year":"2019","author":"Dinan Emily","key":"e_1_2_1_10_1"},{"volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. Association for the Advancement of Artificial Intelligence, 5110\u20135117","year":"2018","author":"Ghazvininejad Marjan","key":"e_1_2_1_11_1"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"e_1_2_1_13_1","first-page":"16","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 1631\u20131640","author":"Gu Jiatao","year":"1865"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4616"},{"volume-title":"Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP'13)","year":"2013","author":"Hassan Ahmed","key":"e_1_2_1_15_1"},{"volume-title":"Proceedings of the 6th International AAAI Conference on Weblogs and Social Media.","year":"2012","author":"Hecht Brent","key":"e_1_2_1_16_1"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3619"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/1625275.1625342"},{"volume-title":"Proceedings of the International Conference on Learning Representations (ICLR'17)","year":"2017","author":"Jang Eric","key":"e_1_2_1_19_1"},{"volume-title":"An information retrieval approach to short text conversation. arXiv preprint arXiv:1408.6988","year":"2014","author":"Ji Zongcheng","key":"e_1_2_1_20_1"},{"volume-title":"Proceedings of the International Conference on Learning Representations (ICLR'17)","author":"Thomas","key":"e_1_2_1_21_1"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5702"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1259"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1138"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1187"},{"volume-title":"Proceedings of the Dialog System Technology Challenge 6 (DSTC6'17)","year":"2017","author":"Long Yinong","key":"e_1_2_1_28_1"},{"volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP'15)","author":"Luong Minh-Thang","key":"e_1_2_1_29_1"},{"volume-title":"Proceedings of the International Conference on Machine Learning (ICML'13)","author":"Maas Andrew L.","key":"e_1_2_1_30_1"},{"key":"e_1_2_1_31_1","unstructured":"Sahisnu Mazumder Nianzu Ma and Bing Liu. 2018. Towards a continuous knowledge learning engine for chatbots. arXiv:1802.06024. Retrieved from https:\/\/arxiv.org\/abs\/1802.06024.  Sahisnu Mazumder Nianzu Ma and Bing Liu. 2018. Towards a continuous knowledge learning engine for chatbots. arXiv:1802.06024. Retrieved from https:\/\/arxiv.org\/abs\/1802.06024."},{"volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP'18)","author":"Moghe Nikita","key":"e_1_2_1_32_1"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1081"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1123"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1237"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1539"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020165.3020183"},{"volume-title":"Presented at the Joensuu Learning and Instruction Symposium","author":"Randolph Justus J.","key":"e_1_2_1_39_1"},{"key":"e_1_2_1_40_1","unstructured":"Pengjie Ren Zhumin Chen Zhaochun Ren Evangelos Kanoulas Christof Monz and Maarten de Rijke. 2020. Conversations with search engines. arxiv:2004.14162. Retrieved fromhttps:\/\/arxiv.org\/abs\/2004.14162.  Pengjie Ren Zhumin Chen Zhaochun Ren Evangelos Kanoulas Christof Monz and Maarten de Rijke. 2020. Conversations with search engines. arxiv:2004.14162. Retrieved fromhttps:\/\/arxiv.org\/abs\/2004.14162."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/2145432.2145500"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/1823431"},{"volume-title":"Advanced Social Interaction with Agents","author":"Rudnicky Alexander I.","key":"e_1_2_1_43_1"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6400"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1152"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1235"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/3304222.3304379"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/3312046"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1253"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1565"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"volume-title":"Proceedings of the International Conference on Learning Representations (ICLR'18)","year":"2018","author":"Veli\u010dkovi\u0107 Petar","key":"e_1_2_1_52_1"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3027063.3053175"},{"volume-title":"Parsing the Turing Test","author":"Wallace Richard S.","key":"e_1_2_1_54_1"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6453"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/365153.365168"},{"volume-title":"Recent Trends in Discourse and Dialogue","author":"Williams Jason D.","key":"e_1_2_1_57_1"},{"volume-title":"Proceedings of the International Conference on Parsing Technologies (IWPT'13)","year":"2013","author":"Wu Xianchao","key":"e_1_2_1_58_1"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00345"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1046"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3421558.3421564"},{"volume-title":"Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI'20), Christian Bessiere (Ed.). International Joint Conferences on","author":"Xu Jun","key":"e_1_2_1_62_1"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6474"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966297"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911542"},{"key":"e_1_2_1_66_1","unstructured":"Lili Yao Ruijian Xu Chao Li Dongyan Zhao and Rui Yan. 2018. Chat more if you like: Dynamic cue words planning to flow longer conversations. arXiv:1811.07631. Retrieved from https:\/\/arxiv.org\/abs\/1811.07631.  Lili Yao Ruijian Xu Chao Li Dongyan Zhao and Rui Yan. 2018. Chat more if you like: Dynamic cue words planning to flow longer conversations. arXiv:1811.07631. Retrieved from https:\/\/arxiv.org\/abs\/1811.07631."},{"volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence.","year":"2018","author":"Young Tom","key":"e_1_2_1_67_1"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3649"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5015"},{"volume-title":"Proceedings of the 32nd AAAI Conference on Artificial Intelligence.","year":"2018","author":"Zhang Wei-Nan","key":"e_1_2_1_70_1"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271776"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1123"},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00683"},{"volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence.","year":"2017","author":"Zhou Hao","key":"e_1_2_1_74_1"},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.5555\/3304222.3304413"},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.635"},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1103"},{"volume-title":"Flexible end-to-end dialogue system for knowledge grounded conversation. arXiv preprint arXiv:1709.04264","year":"2017","author":"Zhu Wenya","key":"e_1_2_1_78_1"},{"volume-title":"Proceedings of the National CCF Conference on Natural Language Processing and Chinese Computing.","year":"2017","author":"Zhuang Yimeng","key":"e_1_2_1_79_1"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3462551","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3462551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:19:02Z","timestamp":1750191542000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3462551"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,12]]},"references-count":79,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,11,30]]}},"alternative-id":["10.1145\/3462551"],"URL":"https:\/\/doi.org\/10.1145\/3462551","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"type":"print","value":"2375-4699"},{"type":"electronic","value":"2375-4702"}],"subject":[],"published":{"date-parts":[[2021,8,12]]},"assertion":[{"value":"2020-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}