{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T00:19:27Z","timestamp":1775175567287,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,4,21]],"date-time":"2018-04-21T00:00:00Z","timestamp":1524268800000},"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":[],"published-print":{"date-parts":[[2018,4,21]]},"DOI":"10.1145\/3173574.3173851","type":"proceedings-article","created":{"date-parts":[[2018,4,20]],"date-time":"2018-04-20T15:43:11Z","timestamp":1524238991000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":41,"title":["Emotional Dialogue Generation using Image-Grounded Language Models"],"prefix":"10.1145","author":[{"given":"Bernd","family":"Huber","sequence":"first","affiliation":[{"name":"Harvard University & Microsoft Research, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"McDuff","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris","family":"Brockett","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michel","family":"Galley","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bill","family":"Dolan","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,4,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/E14-1058"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_3_1","volume-title":"Applications of Computer Vision (WACV), 2016 IEEE Winter Conference on. IEEE, 1--10","author":"Tadas","year":"2016","unstructured":"Tadas Baltru?aitis, Peter Robinson, and Louis-Philippe Morency. 2016. Openface: an open source facial behavior analysis toolkit. In Applications of Computer Vision (WACV), 2016 IEEE Winter Conference on. IEEE, 1--10."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1086\/266520"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/365024.365304"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1067860.1067867"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.5239"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/371552.371555"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025780"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4017"},{"key":"e_1_3_2_1_11_1","unstructured":"Abhishek Das Satwik Kottur Khushi Gupta Avi Singh Deshraj Yadav Jos\u00e9 M. F. Moura Devi Parikh and Dhruv Batra. 2017a. Visual Dialog. (2017). http:\/\/arxiv.org\/abs\/1611.08669"},{"key":"e_1_3_2_1_12_1","volume-title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning. In International Conference on Computer Vision (ICCV). http:\/\/arxiv.org\/abs\/1703","author":"Das Abhishek","year":"2017","unstructured":"Abhishek Das, Satwik Kottur, Jos\u00e9 M. F. Moura, Stefan Lee, and Dhruv Batra. 2017b. Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning. In International Conference on Computer Vision (ICCV). http:\/\/arxiv.org\/abs\/1703.06585"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems. International Foundation for Autonomous Agents and Multiagent Systems, 1061--1068","author":"DeVault David","year":"2014","unstructured":"David DeVault, Ron Artstein, Grace Benn, Teresa Dey, Ed Fast, Alesia Gainer, Kallirroi Georgila, Jon Gratch, Arno Hartholt, Margaux Lhommet, and others. 2014. SimSensei Kiosk: A virtual human interviewer for healthcare decision support. In Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems. International Foundation for Autonomous Agents and Multiagent Systems, 1061--1068."},{"key":"e_1_3_2_1_14_1","volume-title":"Facial action coding system: A technique for the measurement of facial movement. Research Nexus","author":"Ekman Paul","unstructured":"Paul Ekman, Wallace V Friesen, and John Hager. 2002. Facial action coding system: A technique for the measurement of facial movement. Research Nexus, Salt Lake City, UT."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2073"},{"key":"e_1_3_2_1_16_1","volume-title":"Affect-LM: A Neural Language Model for Customizable Affective Text Generation. arXiv preprint arXiv:1704.06851","author":"Ghosh Sayan","year":"2017","unstructured":"Sayan Ghosh, Mathieu Chollet, Eugene Laksana, Louis-Philippe Morency, and Stefan Scherer. 2017. Affect-LM: A Neural Language Model for Customizable Affective Text Generation. arXiv preprint arXiv:1704.06851 (2017)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1124"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74997-4_12"},{"key":"e_1_3_2_1_19_1","unstructured":"Kilem L Gwet. 2014. Handbook of inter-rater reliability: The definitive guide to measuring the extent of agreement among raters. Advanced Analytics LLC."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2005.06.002"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806246"},{"key":"e_1_3_2_1_22_1","volume-title":"Assessment of emotional experience through facial expression","author":"Kassam Karim Sadik","unstructured":"Karim Sadik Kassam. 2010. Assessment of emotional experience through facial expression. Harvard University."},{"key":"e_1_3_2_1_23_1","volume-title":"Computing Krippendorff's alpha reliability. Departmental papers (ASC)","author":"Krippendorff Klaus","year":"2007","unstructured":"Klaus Krippendorff. 2007. Computing Krippendorff's alpha reliability. Departmental papers (ASC) (2007), 43."},{"key":"e_1_3_2_1_24_1","volume-title":"Deep learning. Nature 521, 7553","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1230"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858288"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","unstructured":"Alexander Patrick Mathews Lexing Xie and Xuming He. 2016. SentiCap: Generating Image Descriptions with Sentiments.. In AAAI. 3574--3580.","DOI":"10.5555\/3016387.3016406"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3628"},{"key":"e_1_3_2_1_30_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753587"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858116"},{"key":"e_1_3_2_1_33_1","volume-title":"Image-grounded conversations: Multimodal context for natural question and response generation. arXiv preprint arXiv:1701.08251","author":"Mostafazadeh Nasrin","year":"2017","unstructured":"Nasrin Mostafazadeh, Chris Brockett, Bill Dolan, Michel Galley, Jianfeng Gao, Georgios P Spithourakis, and Lucy Vanderwende. 2017. Image-grounded conversations: Multimodal context for natural question and response generation. arXiv preprint arXiv:1701.08251 (2017)."},{"key":"e_1_3_2_1_34_1","volume-title":"Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, ACL Z16","author":"Mostafazadeh Nasrin","year":"2016","unstructured":"Nasrin Mostafazadeh, Ishan Misra, Jacob Devlin, Margaret Mitchell, Xiaodong He, and Lucy Vanderwende. 2016. Image-grounded conversations: Multimodal context for natural question and response generation. Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, ACL Z16 (2016)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_37_1","volume-title":"MetricsMATR08 workshop. http:\/\/itl.nist.gov\/iad\/mig\/tests\/metricsmatr\/2008\/","author":"Przybocki M.","unstructured":"M. Przybocki, K. Peterson, and S. Bronsart. 2008. Official results of the NIST 2008 Metrics for MAchine TRanslation Challenge. In MetricsMATR08 workshop. http:\/\/itl.nist.gov\/iad\/mig\/tests\/metricsmatr\/2008\/"},{"key":"e_1_3_2_1_38_1","volume-title":"Social interaction skills and nonverbal behavior. Applications of nonverbal behavioral theories and research","author":"Riggio Ronald E","year":"1992","unstructured":"Ronald E Riggio. 1992. Social interaction skills and nonverbal behavior. Applications of nonverbal behavioral theories and research (1992), 3--30."},{"key":"e_1_3_2_1_39_1","volume-title":"Proc. of EMNLP.","author":"Ritter Alan","year":"2011","unstructured":"Alan Ritter, Colin Cherry, and William B Dolan. 2011. Data-driven response generation in social media. In Proc. of EMNLP."},{"key":"e_1_3_2_1_40_1","volume-title":"Proc. of AAAI.","author":"Serban Iulian V","year":"2016","unstructured":"Iulian V Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, and Joelle Pineau. 2016. Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models. In Proc. of AAAI."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Lifeng Shang Zhengdong Lu and Hang Li. 2015. Neural Responding Machine for Short-Text Conversation. In ACL-IJCNLP.","DOI":"10.3115\/v1\/P15-1152"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/642611.642661"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Andrew Shin Yoshitaka Ushiku and Tatsuya Harada. 2016. Image Captioning with Sentiment Terms via Weakly-Supervised Sentiment Dataset. In BMVC.","DOI":"10.5244\/C.30.53"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1020"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. 3104--3112.","DOI":"10.5555\/2969033.2969173"},{"key":"e_1_3_2_1_46_1","volume-title":"Proc. of ICML Deep Learning Workshop.","author":"Vinyals Oriol","year":"2015","unstructured":"Oriol Vinyals and Quoc Le. 2015. A Neural Conversational Model. In Proc. of ICML Deep Learning Workshop."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.3115\/976909.979652"},{"key":"e_1_3_2_1_48_1","volume-title":"Meet xiaoice, cortana's little sister. Microsoft,{Online}. Available: https:\/\/blogs. bing. com\/search\/2014\/09\/05\/meet-xiaoicecortanas-littlesister","author":"Weitz S","year":"2014","unstructured":"S Weitz. 2014. Meet xiaoice, cortana's little sister. Microsoft,{Online}. Available: https:\/\/blogs. bing. com\/search\/2014\/09\/05\/meet-xiaoicecortanas-littlesister (2014)."},{"key":"e_1_3_2_1_49_1","volume-title":"Lina M. Rojas Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, and Steve Young.","author":"Wen Tsung-Hsien","year":"2016","unstructured":"Tsung-Hsien Wen, Milica Gasic, Nikola Mrk\u0161i\u00b4 c, Lina M. Rojas Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, and Steve Young. 2016. Conditional Generation and Snapshot Learning in Neural Dialogue Systems. In EMNLP. ACL, Austin, Texas, 2153--2162. https:\/\/aclweb.org\/anthology\/D16--1233"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2971475"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","unstructured":"Bolei Zhou Agata Lapedriza Jianxiong Xiao Antonio Torralba and Aude Oliva. 2014. Learning deep features for scene recognition using places database. In Advances in neural information processing systems. 487--495.","DOI":"10.5555\/2968826.2968881"}],"event":{"name":"CHI '18: CHI Conference on Human Factors in Computing Systems","location":"Montreal QC Canada","acronym":"CHI '18","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3173574.3173851","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3173574.3173851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:41Z","timestamp":1750208921000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3173574.3173851"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,21]]},"references-count":52,"alternative-id":["10.1145\/3173574.3173851","10.1145\/3173574"],"URL":"https:\/\/doi.org\/10.1145\/3173574.3173851","relation":{},"subject":[],"published":{"date-parts":[[2018,4,21]]},"assertion":[{"value":"2018-04-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}