AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

AI 精读

AI抽取本论文的概要总结


微博一下
We propose a novel way to generate empathetic dialogue responses by using Mixture of Empathetic Listeners

MoEL: Mixture of Empathetic Listeners

EMNLP/IJCNLP (1), pp.121-132, (2019)

被引用9|浏览623
EI
下载 PDF 全文
引用
微博一下

摘要

Previous research on empathetic dialogue systems has mostly focused on generating responses given certain emotions. However, being empathetic not only requires the ability of generating emotional responses, but more importantly, requires the understanding of user emotions and replying appropriately. In this paper, we propose a novel end...更多

代码

数据

简介
  • Neural network approaches for conversation models have shown to be successful in scalable training and generating fluent and relevant responses (Vinyals and Le, 2015).
  • Many others have shown that the incorporation of additional inductive bias leads to a more engaging chatbot, such as understanding commonsense (Dinan et al, 2018), or modeling consistent persona (Li et al, 2016b; Zhang et al, 2018a; Mazare et al, 2018a)
  • Another important aspect of an engaging human conversation that received rela- Emotion: Angry.
重点内容
  • Neural network approaches for conversation models have shown to be successful in scalable training and generating fluent and relevant responses (Vinyals and Le, 2015)
  • We propose a novel way to generate empathetic dialogue responses by using Mixture of Empathetic Listeners (MoEL)
  • Our experimental results show that Mixture of Empathetic Listeners is able to achieve competitive performance in the task with the advantage of being more interpretable than other conventional models
  • Having a persona would allow the system to have more consistent and personalized responses, and combining open-domain conversations with task-oriented dialogue systems would equip the system with more engaging conversational capabilities, resulting in a more versatile dialogue system
结果
  • Emotion detection To verify whether the model can attend to the appropriate listeners, the authors compute the emotion detection accuracy for each turn.
  • The authors' model achieve 38%, 63%, 74% in terms of top-1, top-3, top-5 detection accuracy over 32 emotions.
  • The authors notice that some emotions frequently appear in similar context (e.g., Annoyed, Angry, Furious) which might degrade the detection accuracy.
  • The authors can see that by using top-5 the majority of the emotion achieve around 80% accuracy.
  • The authors assign three human annotators to score the following aspect of models: Empathy, Relevance, and Fluency.
  • Note that the authors evaluate each metric independently and the scores range
结论
  • Conclusion & Future

    Work

    In this paper, the authors propose a novel way to generate empathetic dialogue responses by using Mixture of Empathetic Listeners (MoEL).
  • The authors benchmark the model in empathetic-dialogues dataset (Rashkin et al, 2018), which is a multiturn open-domain conversation corpus grounded on emotional situations.
  • The authors show that the model is able to automatically select the correct emotional decoder and effectively generate an empathetic response.
  • Having a persona would allow the system to have more consistent and personalized responses, and combining open-domain conversations with task-oriented dialogue systems would equip the system with more engaging conversational capabilities, resulting in a more versatile dialogue system
表格
  • Table1: One conversation from empathetic dialogue, a speaker tells the situation he(she) is facing, and a listener try to understand speaker’s feeling and respond accordingly tively less focus is emotional understanding and empathy (<a class="ref-link" id="cRashkin_et+al_2018_a" href="#rRashkin_et+al_2018_a">Rashkin et al, 2018</a>; <a class="ref-link" id="cDinan_et+al_2019_a" href="#rDinan_et+al_2019_a">Dinan et al, 2019</a>; <a class="ref-link" id="cWolf_et+al_2019_a" href="#rWolf_et+al_2019_a">Wolf et al, 2019</a>). Intuitively, ordinary social conversations between two humans are often about their daily lives that revolve around happy or sad experiences. In such scenarios, people generally tend to respond in a way that acknowledges the feelings of their conversational partners
  • Table2: Comparison between our proposed methods and baselines. All of models receive close BLEU score. MoEL achieve highest Empathy and Relevance score, while TRS achieve better Fluency score. The number of parameters for each model is reported
  • Table3: Result of human A/B test. Tests are conducted pairwise between MoEL and baseline models
  • Table4: Generated responses from TRS, Multi-TRS and MoEL in 2 different user emotion states (top) and comparing generation from different listeners (bottom). We use hard attention on Terrified, Sad, Excited and Proud listeners
Download tables as Excel
相关工作
基金
  • This work has been partially funded by ITF/319/16FP and MRP/055/18 of the Innovation Technology Commission, the Hong Kong SAR Government
引用论文
  • Rahaf Aljundi, Punarjay Chakravarty, and Tinne Tuytelaars. 2017. Expert gate: Lifelong learning with a network of experts. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3366–3375.
    Google ScholarLocate open access versionFindings
  • Dario Bertero, Farhad Bin Siddique, Chien-Sheng Wu, Yan Wan, Ricky Ho Yin Chan, and Pascale Fung. 2016. Real-time speech emotion and sentiment recognition for interactive dialogue systems. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1042– 1047.
    Google ScholarLocate open access versionFindings
  • Deng Cai, Yan Wang, Victoria Bi, Zhaopeng Tu, Xiaojiang Liu, Wai Lam, and Shuming Shi. 2018. Skeleton-to-response: Dialogue generation guided by retrieval memory. arXiv preprint arXiv:1809.05296.
    Findings
  • Ankush Chatterjee, Umang Gupta, Manoj Kumar Chinnakotla, Radhakrishnan Srikanth, Michel Galley, and Puneet Agrawal. 2019a. Understanding emotions in text using deep learning and big data. Computers in Human Behavior, 93:309–317.
    Google ScholarLocate open access versionFindings
  • Ankush Chatterjee, Kedhar Nath Narahari, Meghana Joshi, and Puneet Agrawal. 2019b. Semeval-2019 task 3: Emocontext: Contextual emotion detection in text. In Proceedings of The 13th International Workshop on Semantic Evaluation (SemEval-2019), Minneapolis, Minnesota.
    Google ScholarLocate open access versionFindings
  • Ronan Collobert, Samy Bengio, and Yoshua Bengio. 2002. A parallel mixture of svms for very large scale problems. In Advances in Neural Information Processing Systems, pages 633–640.
    Google ScholarLocate open access versionFindings
  • Marc Deisenroth and Jun Wei Ng. 2015. Distributed gaussian processes. In International Conference on Machine Learning, pages 1481–1490.
    Google ScholarLocate open access versionFindings
  • Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 201Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
    Findings
  • Emily Dinan, Varvara Logacheva, Valentin Malykh, Alexander Miller, Kurt Shuster, Jack Urbanek, Douwe Kiela, Arthur Szlam, Iulian Serban, Ryan Lowe, et al. 201The second conversational intelligence challenge (convai2). arXiv preprint arXiv:1902.00098.
    Findings
  • Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. 2018. Wizard of wikipedia: Knowledge-powered conversational agents. ICLR.
    Google ScholarLocate open access versionFindings
  • Yingruo Fan, Jacqueline CK Lam, and Victor OK Li. 2018a. Multi-region ensemble convolutional neural network for facial expression recognition. In International Conference on Artificial Neural Networks, pages 84–94. Springer.
    Google ScholarLocate open access versionFindings
  • Yingruo Fan, Jacqueline CK Lam, and Victor OK Li. 2018b. Unsupervised domain adaptation with generative adversarial networks for facial emotion recognition. In 2018 IEEE International Conference on Big Data (Big Data), pages 4460–4464. IEEE.
    Google ScholarLocate open access versionFindings
  • Yingruo Fan, Jacqueline CK Lam, and Victor OK Li. 2018c. Video-based emotion recognition using deeply-supervised neural networks. In Proceedings of the 2018 on International Conference on Multimodal Interaction, pages 584–588. ACM.
    Google ScholarLocate open access versionFindings
  • Jianfeng Gao, Michel Galley, and Lihong Li. 2018. Neural approaches to conversational ai. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pages 1371–1374. ACM.
    Google ScholarLocate open access versionFindings
  • Braden Hancock, Antoine Bordes, Pierre-Emmanuel Mazare, and Jason Weston. 2019. Learning from dialogue after deployment: Feed yourself, chatbot! arXiv preprint arXiv:1901.05415.
    Findings
  • Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. 2017. Toward controlled generation of text. In International Conference on Machine Learning, pages 1587–1596.
    Google ScholarLocate open access versionFindings
  • Robert A Jacobs, Michael I Jordan, Steven J Nowlan, Geoffrey E Hinton, et al. 1991. Adaptive mixtures of local experts. Neural computation, 3(1):79–87.
    Google ScholarLocate open access versionFindings
  • Michael I Jordan and Robert A Jacobs. 1994. Hierarchical mixtures of experts and the em algorithm. Neural computation, 6(2):181–214.
    Google ScholarLocate open access versionFindings
  • Chaitanya K Joshi, Fei Mi, and Boi Faltings. 2017. Personalization in goal-oriented dialog. arXiv preprint arXiv:1706.07503.
    Findings
  • Lukasz Kaiser, Aidan N Gomez, Noam Shazeer, Ashish Vaswani, Niki Parmar, Llion Jones, and Jakob Uszkoreit. 2017. One model to learn them all. arXiv preprint arXiv:1706.05137.
    Findings
  • Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
    Findings
  • Ilya Kulikov, Alexander H Miller, Kyunghyun Cho, and Jason Weston. 2018. Importance of a search strategy in neural dialogue modelling. arXiv preprint arXiv:1811.00907.
    Findings
  • Nayeon Lee, Zihan Liu, and Pascale Fung. 2019. Team yeon-zi at semeval-2019 task 4: Hyperpartisan news detection by de-noising weakly-labeled data. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 1052–1056.
    Google ScholarLocate open access versionFindings
  • Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016a. A diversity-promoting objective function for neural conversation models. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 110–119.
    Google ScholarLocate open access versionFindings
  • Jiwei Li, Michel Galley, Chris Brockett, Georgios Spithourakis, Jianfeng Gao, and Bill Dolan. 2016b. A persona-based neural conversation model. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 994–1003.
    Google ScholarLocate open access versionFindings
  • Jiwei Li, Will Monroe, Alan Ritter, Dan Jurafsky, Michel Galley, and Jianfeng Gao. 2016c. Deep reinforcement learning for dialogue generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1192– 1202.
    Google ScholarLocate open access versionFindings
  • Chia-Wei Liu, Ryan Lowe, Iulian Serban, Mike Noseworthy, Laurent Charlin, and Joelle Pineau. 2016. How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2122–2132.
    Google ScholarLocate open access versionFindings
  • Nurul Lubis, Sakriani Sakti, Koichiro Yoshino, and Satoshi Nakamura. 2018. Eliciting positive emotion through affect-sensitive dialogue response generation: A neural network approach. In Thirty-Second AAAI Conference on Artificial Intelligence.
    Google ScholarLocate open access versionFindings
  • Andrea Madotto, Zhaojiang Lin, Chien-Sheng Wu, and Pascale Fung. 2019. Personalizing dialogue agents via meta-learning. In Proceedings of the 57th Conference of the Association for Computational Linguistics, pages 5454–5459.
    Google ScholarLocate open access versionFindings
  • Andrea Madotto, Chien-Sheng Wu, and Pascale Fung. 2018. Mem2seq: Effectively incorporating knowledge bases into end-to-end task-oriented dialog systems. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1468–1478.
    Google ScholarLocate open access versionFindings
  • Pierre-Emmanuel Mazare, Samuel Humeau, Martin Raison, and Antoine Bordes. 2018a. Training millions of personalized dialogue agents. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2775–2779.
    Google ScholarLocate open access versionFindings
  • Pierre-Emmanuel Mazare, Samuel Humeau, Martin Raison, and Antoine Bordes. 2018b. Training millions of personalized dialogue agents. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2775–2779. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Alexander Miller, Adam Fisch, Jesse Dodge, AmirHossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-value memory networks for directly reading documents. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1400–1409.
    Google ScholarLocate open access versionFindings
  • Kishore Papineni, Salim Roukos, Todd Ward, and WeiJing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting on association for computational linguistics, pages 311–318. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543.
    Google ScholarLocate open access versionFindings
  • Dinesh Raghu, Nikhil Gupta, and Mausam. 2019. Disentangling Language and Knowledge in TaskOriented Dialogs. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1239–1255, Minneapolis, Minnesota. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. 2018. I know the feeling: Learning to converse with empathy. arXiv preprint arXiv:1811.00207.
    Findings
  • Carl E Rasmussen and Zoubin Ghahramani. 2002. Infinite mixtures of gaussian process experts. In Advances in neural information processing systems, pages 881–888.
    Google ScholarLocate open access versionFindings
  • Revanth Reddy, Danish Contractor, Dinesh Raghu, and Sachindra Joshi. 2018. Multi-level memory for task oriented dialogs. arXiv preprint arXiv:1810.10647.
    Findings
  • Jurgen Schmidhuber. 1987. Evolutionary principles in self-referential learning. on learning now to learn: The meta-meta-meta...-hook. Diploma thesis, Technische Universitat Munchen, Germany, 14 May.
    Google ScholarFindings
  • Iulian Vlad Serban, Ryan Lowe, Laurent Charlin, and Joelle Pineau. 2016. Generative deep neural networks for dialogue: A short review. arXiv preprint arXiv:1611.06216.
    Findings
  • Babak Shahbaba and Radford Neal. 2009. Nonlinear models using dirichlet process mixtures. Journal of Machine Learning Research, 10(Aug):1829–1850.
    Google ScholarLocate open access versionFindings
  • Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538.
    Findings
  • Jamin Shin, Peng Xu, Andrea Madotto, and Pascale Fung. 2019. Happybot: Generating empathetic dialogue responses by improving user experience lookahead. arXiv preprint arXiv:1906.08487.
    Findings
  • Lucas Theis and Matthias Bethge. 2015. Generative image modeling using spatial lstms. In Advances in Neural Information Processing Systems, pages 1927–1935.
    Google ScholarLocate open access versionFindings
  • Volker Tresp. 2001. Mixtures of gaussian processes. In Advances in neural information processing systems, pages 654–660.
    Google ScholarLocate open access versionFindings
  • Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems, pages 5998–6008.
    Google ScholarLocate open access versionFindings
  • Oriol Vinyals and Quoc Le. 2015. A neural conversational model. In International Conference on Machine Learning.
    Google ScholarLocate open access versionFindings
  • Ke Wang and Xiaojun Wan. 2018. Sentigan: generating sentimental texts via mixture adversarial networks. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, pages 4446–4452. AAAI Press.
    Google ScholarLocate open access versionFindings
  • Jason Weston, Emily Dinan, and Alexander Miller. 2018. Retrieve and refine: Improved sequence generation models for dialogue. In Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI, pages 87–92.
    Google ScholarLocate open access versionFindings
  • Genta Indra Winata, Onno Kampman, Yang Yang, Anik Dey, and Pascale Fung. 2017. Nora the empathetic psychologist. Proc. Interspeech 2017, pages 3437–3438.
    Google ScholarLocate open access versionFindings
  • Genta Indra Winata, Andrea Madotto, Zhaojiang Lin, Jamin Shin, Yan Xu, Peng Xu, and Pascale Fung. 2019. Caire hkust at semeval-2019 task 3: Hierarchical attention for dialogue emotion classification. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 142–147.
    Google ScholarLocate open access versionFindings
  • Thomas Wolf, Victor Sanh, Julien Chaumond, and Clement Delangue. 2019. Transfertransfo: A transfer learning approach for neural network based conversational agents. arXiv preprint arXiv:1901.08149.
    Findings
  • Chien-Sheng Wu, Andrea Madotto, Genta Winata, and Pascale Fung. 2017. End-to-end recurrent entity network for entity-value independent goal-oriented dialog learning. In Dialog System Technology Challenges Workshop, DSTC6.
    Google ScholarLocate open access versionFindings
  • Chien-Sheng Wu, Andrea Madotto, Genta Indra Winata, and Pascale Fung. 2018a. End-to-end dynamic query memory network for entity-value independent task-oriented dialog. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 6154–6158. IEEE.
    Google ScholarLocate open access versionFindings
  • Chien-Sheng Wu, Richard Socher, and Caiming Xiong. 2019. Global-to-local memory pointer networks for task-oriented dialogue. arXiv preprint arXiv:1901.04713.
    Findings
  • Yu Wu, Furu Wei, Shaohan Huang, Zhoujun Li, and Ming Zhou. 2018b. Response generation by context-aware prototype editing. arXiv preprint arXiv:1806.07042.
    Findings
  • Peng Xu, Andrea Madotto, Chien-Sheng Wu, Ji Ho Park, and Pascale Fung. 2018. Emo2vec: Learning generalized emotion representation by multitask training. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 292–298.
    Google ScholarLocate open access versionFindings
  • Bangpeng Yao, Dirk Walther, Diane Beck, and Li FeiFei. 2009. Hierarchical mixture of classification experts uncovers interactions between brain regions. In Advances in Neural Information Processing Systems, pages 2178–2186.
    Google ScholarLocate open access versionFindings
  • Semih Yavuz, Abhinav Rastogi, Guanlin Chao, Dilek Hakkani-Tur, and Amazon Alexa AI. 2018. Deepcopy: Grounded response generation with hierarchical pointer networks. ConvAI Workshop@NIPS.
    Google ScholarFindings
  • Yury Zemlyanskiy and Fei Sha. 2018. Aiming to know you better perhaps makes me a more engaging dialogue partner. CoNLL 2018, page 551.
    Google ScholarLocate open access versionFindings
  • Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018a. Personalizing dialogue agents: I have a dog, do you have pets too? In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2204– 2213.
    Google ScholarLocate open access versionFindings
  • Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018b. Personalizing dialogue agents: I have a dog, do you have pets too? In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2204– 2213. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, and Bing Liu. 2018. Emotional chatting machine: Emotional conversation generation with internal and external memory. In Thirty-Second AAAI Conference on Artificial Intelligence.
    Google ScholarLocate open access versionFindings
  • Xianda Zhou and William Yang Wang. 2018. Mojitalk: Generating emotional responses at scale. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1128–1137.
    Google ScholarLocate open access versionFindings
您的评分 :
0

 

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科