Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Target-guided Emotion-aware Chat Machine

Target-guided Emotion-aware Chat Machine The consistency of a response to a given post at the semantic level and emotional level is essential for a dialogue system to deliver humanlike interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem and proposes a unified end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post and leveraging target information to generate more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Information Systems (TOIS) Association for Computing Machinery

Target-guided Emotion-aware Chat Machine

Download PDF
24 pages

Loading next page...
 
/lp/association-for-computing-machinery/target-guided-emotion-aware-chat-machine-ncw0cUrnJ0

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Association for Computing Machinery
Copyright
Copyright © 2021 Association for Computing Machinery.
ISSN
1046-8188
eISSN
1558-2868
DOI
10.1145/3456414
Publisher site
See Article on Publisher Site

Abstract

The consistency of a response to a given post at the semantic level and emotional level is essential for a dialogue system to deliver humanlike interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem and proposes a unified end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post and leveraging target information to generate more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness.

Journal

ACM Transactions on Information Systems (TOIS) – Association for Computing Machinery

Published: Aug 17, 2021

Keywords: Dialogue generation

References

  • Neural machine translation by jointly learning to align and translate
    Bahdanau, Dzmitry; Cho, Kyunghyun; Bengio, Yoshua
  • Predicting user mental states in spoken dialogue systems
    Callejas, Zoraida; Griol, David; López-Cózar, Ramón
  • Learning phrase representations using RNN encoder-decoder for statistical machine translation
    Cho, Kyunghyun; Van Merriënboer, Bart; Gulcehre, Caglar; Bahdanau, Dzmitry; Bougares, Fethi; Schwenk, Holger; Bengio, Yoshua
  • Bert: Pre-training of deep bidirectional transformers for language understanding
    Devlin, Jacob; Chang, Ming-Wei; Lee, Kenton; Toutanova, Kristina
  • Adaptive subgradient methods for online learning and stochastic optimization
    Duchi, John; Hazan, Elad; Singer, Yoram
  • The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability
    Fleiss, Joseph L.; Cohen, Jacob
  • Affect-lm: A neural language model for customizable affective text generation
    Ghosh, Sayan; Chollet, Mathieu; Laksana, Eugene; Morency, Louis-Philippe; Scherer, Stefan
  • Long short-term memory
    Hochreiter, Sepp; Schmidhuber, Jürgen
  • Convolutional neural network architectures for matching natural language sentences
    Hu, Baotian; Lu, Zhengdong; Li, Hang; Chen, Qingcai
  • Toward controlled generation of text
    Hu, Zhiting; Yang, Zichao; Liang, Xiaodan; Salakhutdinov, Ruslan; Xing, Eric P.
  • Automatic dialogue generation with expressed emotions
    Huang, Chenyang; Zaiane, Osmar; Trabelsi, Amine; Dziri, Nouha
  • On using very large target vocabulary for neural machine translation
    Jean, Sébastien; Cho, Kyunghyun; Memisevic, Roland; Bengio, Yoshua
  • An information retrieval approach to short text conversation (unpublished)
    Ji, Zongcheng; Lu, Zhengdong; Li, Hang
  • A diversity-promoting objective function for neural conversation models
    Li, Jiwei; Galley, Michel; Brockett, Chris; Gao, Jianfeng; Dolan, Bill
  • A persona-based neural conversation model
    Li, Jiwei; Galley, Michel; Brockett, Chris; Spithourakis, Georgios P.; Gao, Jianfeng; Dolan, Bill
  • A simple, fast diverse decoding algorithm for neural generation
    Li, Jiwei; Monroe, Will; Jurafsky, Dan
  • EmpDG: Multi-resolution interactive empathetic dialogue generation
    Li, Qintong; Chen, Hongshen; Ren, Zhaochun; Chen, Zhumin; Tu, Zhaopeng; Ma, Jun
  • A structured self-attentive sentence embedding (unpublished)
    Lin, Zhouhan; Feng, Minwei; Santos, Cicero Nogueira dos; Yu, Mo; Xiang, Bing; Zhou, Bowen; Bengio, Yoshua
  • How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation
    Liu, Chia-Wei; Lowe, Ryan; Serban, Iulian V.; Noseworthy, Michael; Charlin, Laurent; Pineau, Joelle
  • The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems
    Lowe, Ryan; Pow, Nissan; Serban, Iulian; Pineau, Joelle
  • A deep architecture for matching short texts
    Lu, Zhengdong; Li, Hang
  • Effective approaches to attention-based neural machine translation
    Luong, Minh-Thang; Pham, Hieu; Manning, Christopher D.
  • Breakdown in human-machine interaction: the error is the clue
    Martinovski, Bilyana; Traum, David
  • Human abilities: Emotional intelligence
    Mayer, John D.; Roberts, Richard D.; Barsade, Sigal G.
  • Efficient estimation of word representations in vector space
    Mikolov, Tomas; Chen, Kai; Corrado, Greg; Dean, Jeffrey
  • Sequence to backward and forward sequences: A content-introducing approach to generative short-text conversation
    Mou, Lili; Song, Yiping; Yan, Rui; Li, Ge; Zhang, Lu; Jin, Zhi
  • BLEU: A method for automatic evaluation of machine translation
    Papineni, Kishore; Roukos, Salim; Ward, Todd; Zhu, Wei-Jing
  • Topic-enhanced emotional conversation generation with attention mechanism
    Peng, Yehong; Fang, Yizhen; Xie, Zhiwen; Zhou, Guangyou
  • A general psychoevolutionary theory of emotion
    Plutchik, Robert
  • The nature of emotions: Human emotions have deep evolutionary roots, a fact that may explain their complexity and provide tools for clinical practice
    Plutchik, Robert
  • Using human physiology to evaluate subtle expressivity of a virtual quizmaster in a mathematical game
    Prendinger, Helmut; Mori, Junichiro; Ishizuka, Mitsuru
  • Assigning personality/identity to a chatting machine for coherent conversation generation
    Qian, Qiao; Huang, Minlie; Zhao, Haizhou; Xu, Jingfang; Zhu, Xiaoyan
  • Data-driven response generation in social media
    Ritter, Alan; Cherry, Colin; Dolan, William B.
  • Building end-to-end dialogue systems using generative hierarchical neural network models
    Serban, Iulian Vlad; Sordoni, Alessandro; Bengio, Yoshua; Courville, Aaron C.; Pineau, Joelle
  • A hierarchical latent variable encoder-decoder model for generating dialogues
    Serban, Iulian Vlad; Sordoni, Alessandro; Lowe, Ryan; Charlin, Laurent; Pineau, Joelle; Courville, Aaron; Bengio, Yoshua
  • Neural responding machine for short-text conversation
    Shang, Lifeng; Lu, Zhengdong; Li, Hang
  • Directional skip-gram: Explicitly distinguishing left and right context for word embeddings
    Song, Yan; Shi, Shuming; Li, Jing; Zhang, Haisong
  • Generating responses with a specific emotion in dialog
    Song, Zhenqiao; Zheng, Xiaoqing; Liu, Lu; Xu, Mu; Huang, Xuan-Jing
  • A neural network approach to context-sensitive generation of conversational responses
    Sordoni, Alessandro; Galley, Michel; Auli, Michael; Brockett, Chris; Ji, Yangfeng; Mitchell, Margaret; Nie, Jian-Yun; Gao, Jianfeng; Dolan, Bill
  • Sequence to sequence learning with neural networks
    Sutskever, Ilya; Vinyals, Oriol; Le, Quoc V.
  • Learning sentiment-specific word embedding for twitter sentiment classification
    Tang, Duyu; Wei, Furu; Yang, Nan; Zhou, Ming; Liu, Ting; Qin, Bing
  • Multi-representation fusion network for multi-turn response selection in retrieval-based chatbots
    Tao, Chongyang; Wu, Wei; Xu, Can; Hu, Wenpeng; Zhao, Dongyan; Yan, Rui
  • Attention is all you need
    Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; Uszkoreit, Jakob; Jones, Llion; Gomez, Aidan N.; Kaiser, Łukasz; Polosukhin, Illia
  • Diverse beam search: Decoding diverse solutions from neural sequence models
    Vijayakumar, Ashwin K.; Cogswell, Michael; Selvaraju, Ramprasath R.; Sun, Qing; Lee, Stefan; Crandall, David; Batra, Dhruv
  • Grammar as a foreign language
    Vinyals, Oriol; Kaiser, Łukasz; Koo, Terry; Petrov, Slav; Sutskever, Ilya; Hinton, Geoffrey
  • A neural conversational model
    Vinyals, Oriol; Le, Quoc
  • The Elements of AIML Style
    Wallace, Richard
  • A dataset for research on short-text conversations
    Wang, Hao; Lu, Zhengdong; Li, Hang; Chen, Enhong
  • Integrating community question and answer archives
    Wei, Wei; Cong, Gao; Li, Xiaoli; Ng, See-Kiong; Li, Guohui
  • Emotion-aware chat machine: Automatic emotional response generation for human-like emotional interaction
    Wei, Wei; Liu, Jiayi; Mao, Xianling; Guo, Guibing; Zhu, Feida; Zhou, Pan; Hu, Yuchong
  • Exploring heterogeneous features for query-focused summarization of categorized community answers
    Wei, Wei; Ming, ZhaoYan; Nie, Liqiang; Li, Guohui; Li, Jianjun; Zhu, Feida; Shang, Tianfeng; Luo, Changyin
  • ELIZA: A computer program for the study of natural language communication between man and machine
    Weizenbaum, Joseph
  • Beyond Façade: Pattern Matching for Natural Language Applications
    Wilcox, Bruce
  • Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots
    Wu, Yu; Wu, Wei; Xing, Chen; Zhou, Ming; Li, Zhoujun
  • Topic aware neural response generation
    Xing, Chen; Wu, Wei; Wu, Yu; Liu, Jie; Huang, Yalou; Zhou, Ming; Ma, Wei-Ying
  • Learning to respond with deep neural networks for retrieval-based human-computer conversation system
    Yan, Rui; Song, Yiping; Wu, Hua
  • Tailored sequence to sequence models to different conversation scenarios
    Zhang, Hainan; Lan, Yanyan; Guo, Jiafeng; Xu, Jun; Cheng, Xueqi
  • Emotional chatting machine: Emotional conversation generation with internal and external memory
    Zhou, Hao; Huang, Minlie; Zhang, Tianyang; Zhu, Xiaoyan; Liu, Bing
  • Commonsense knowledge aware conversation generation with graph attention
    Zhou, Hao; Young, Tom; Huang, Minlie; Zhao, Haizhou; Xu, Jingfang; Zhu, Xiaoyan
  • The design and implementation of xiaoice, an empathetic social chatbot
    Zhou, Li; Gao, Jianfeng; Li, Di; Shum, Heung-Yeung
  • Multi-view response selection for human-computer conversation
    Zhou, Xiangyang; Dong, Daxiang; Wu, Hua; Zhao, Shiqi; Yu, Dianhai; Tian, Hao; Liu, Xuan; Yan, Rui
  • Multi-turn response selection for chatbots with deep attention matching network
    Zhou, Xiangyang; Li, Lu; Dong, Daxiang; Liu, Yi; Chen, Ying; Zhao, Wayne Xin; Yu, Dianhai; Wu, Hua
  • Mojitalk: Generating emotional responses at scale
    Zhou, Xianda; Wang, William Yang