Simulated Annealing for Emotional Dialogue Systems

Explicitly modeling emotions in dialogue generation has important applications, such as building empathetic personal companions. In this study, we consider the task of expressing a specific emotion for dialogue generation. Previous approaches take the emotion as a training signal, which may be ignored during inference. Here, we propose a search-based emotional dialogue system by simulated annealing (SA). Specifically, we first define a scoring function that combines contextual coherence and emotional correctness. Then, SA iteratively edits a general response, and search for a generation with a high score. In this way, we enforce the presence of the desired emotion. We evaluate our system on the NLPCC2017 dataset. The proposed method shows about 12% improvements in emotion accuracy compared with the previous state-of-the-art method, without hurting the generation quality (measured by BLEU).

[1]  Jesse Hoey,et al.  Affective Neural Response Generation , 2017, ECIR.

[2]  Verena Rieser,et al.  Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity , 2018, EMNLP.

[3]  P. Ekman.  Expression and the Nature of Emotion , 1984 .

[4]  Rada Mihalcea,et al.  MIME: MIMicking Emotions for Empathetic Response Generation , 2020, EMNLP.

[5]  Jon Rokne,et al.  Emotion detection from text and speech: a survey , 2018, Social Network Analysis and Mining.

[6]  Lei Li,et al.  CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling , 2018, AAAI.

[7]  Jianfeng Gao,et al.  A Diversity-Promoting Objective Function for Neural Conversation Models , 2015, NAACL.

[8]  Osmar R. Zaïane,et al.  ANA at SemEval-2019 Task 3: Contextual Emotion detection in Conversations through hierarchical LSTMs and BERT , 2019, *SEMEVAL.

[9]  Lili Mou,et al.  Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction , 2020, ACL.

[10]  Lili Mou,et al.  Seq2Emo: A Sequence to Multi-Label Emotion Classification Model , 2021, NAACL.

[11]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[12]  Michael R. Lyu,et al.  Unsupervised Text Generation by Learning from Search , 2020, NeurIPS.

[13]  R. Plutchik.  A GENERAL PSYCHOEVOLUTIONARY THEORY OF EMOTION , 1980 .

[14]  Xiaoyan Zhu,et al.  Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory , 2017, AAAI.

[15]  Jianfeng Gao,et al.  A Persona-Based Neural Conversation Model , 2016, ACL.

[16]  Joelle Pineau,et al.  How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation , 2016, EMNLP.

[17]  Osmar R. Zaïane,et al.  Automatic Dialogue Generation with Expressed Emotions , 2018, NAACL.

[18]  Rui Yan,et al.  Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation , 2016, COLING.

[19]  Lili Mou,et al.  Iterative Edit-Based Unsupervised Sentence Simplification , 2020, ACL.

[20]  Wei-Ying Ma,et al.  Topic Aware Neural Response Generation , 2016, AAAI.

[21]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[22]  Jie Zhou,et al.  Unsupervised Paraphrasing by Simulated Annealing , 2019, ACL.

[23]  Xuanjing Huang,et al.  Generating Responses with a Specific Emotion in Dialog , 2019, ACL.

[24]  Yoav Goldberg,et al.  Controlling Linguistic Style Aspects in Neural Language Generation , 2017, ArXiv.

[25]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[26]  Osmar R. Zaïane,et al.  Current State of Text Sentiment Analysis from Opinion to Emotion Mining , 2017, ACM Comput. Surv..

[27]  C. Miao,et al.  Towards Persona-Based Empathetic Conversational Models , 2020, EMNLP.

[28]  Yang Feng,et al.  CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation , 2020, ACL.