{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/an-affect-rich-neural-conversational-model","title":"An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss","arxiv_id":"1811.07078","date":"2018-11-17","proceeding":null,"authors":["Peixiang Zhong","Di Wang","Chunyan Miao"],"abstract":"Affect conveys important implicit information in human communication. Having\nthe capability to correctly express affect during human-machine conversations\nis one of the major milestones in artificial intelligence. In recent years,\nextensive research on open-domain neural conversational models has been\nconducted. However, embedding affect into such models is still under explored.\nIn this paper, we propose an end-to-end affect-rich open-domain neural\nconversational model that produces responses not only appropriate in syntax and\nsemantics, but also with rich affect. Our model extends the Seq2Seq model and\nadopts VAD (Valence, Arousal and Dominance) affective notations to embed each\nword with affects. In addition, our model considers the effect of negators and\nintensifiers via a novel affective attention mechanism, which biases attention\ntowards affect-rich words in input sentences. Lastly, we train our model with\nan affect-incorporated objective function to encourage the generation of\naffect-rich words in the output responses. Evaluations based on both perplexity\nand human evaluations show that our model outperforms the state-of-the-art\nbaseline model of comparable size in producing natural and affect-rich\nresponses.","url_abs":"http://arxiv.org/abs/1811.07078v1","url_pdf":"http://arxiv.org/pdf/1811.07078v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"an-affect-rich-neural-conversational-model","repo_url":"https://github.com/zhongpeixiang/affect-rich-conversational-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.07078","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}