Exploiting Emotion-Semantic Correlations for Empathetic Response Generation (2402.17437v1)
Abstract: Empathetic response generation aims to generate empathetic responses by understanding the speaker's emotional feelings from the language of dialogue. Recent methods capture emotional words in the language of communicators and construct them as static vectors to perceive nuanced emotions. However, linguistic research has shown that emotional words in language are dynamic and have correlations with other grammar semantic roles, i.e., words with semantic meanings, in grammar. Previous methods overlook these two characteristics, which easily lead to misunderstandings of emotions and neglect of key semantics. To address this issue, we propose a dynamical Emotion-Semantic Correlation Model (ESCM) for empathetic dialogue generation tasks. ESCM constructs dynamic emotion-semantic vectors through the interaction of context and emotions. We introduce dependency trees to reflect the correlations between emotions and semantics. Based on dynamic emotion-semantic vectors and dependency trees, we propose a dynamic correlation graph convolutional network to guide the model in learning context meanings in dialogue and generating empathetic responses. Experimental results on the EMPATHETIC-DIALOGUES dataset show that ESCM understands semantics and emotions more accurately and expresses fluent and informative empathetic responses. Our analysis results also indicate that the correlations between emotions and semantics are frequently used in dialogues, which is of great significance for empathetic perception and expression.
- Danqi Chen and Christopher D Manning. 2014. A fast and accurate dependency parser using neural networks. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 740–750.
- René Dirven. 1997. Emotions as cause and the cause of emotions. The language of emotions, pages 55–84.
- Timothy Dozat and Christopher D Manning. 2016. Deep biaffine attention for neural dependency parsing. arXiv preprint arXiv:1611.01734.
- Joseph L Fleiss and Jacob Cohen. 1973. The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability. Educational and psychological measurement, 33(3):613–619.
- Moving ourselves, moving others: Motion and emotion in intersubjectivity, consciousness and language. John Benjamins Publishing Company.
- Improving empathetic response generation by recognizing emotion cause in conversations. In Findings of EMNLP, pages 807–819.
- Perspective-taking and pragmatics for generating empathetic responses focused on emotion causes. In EMNLP.
- Emp-rft: Empathetic response generation via recognizing feature transitions between utterances. arXiv preprint arXiv:2205.03112.
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:abs/1412.6980.
- Eliyahu Kiperwasser and Yoav Goldberg. 2016. Simple and accurate dependency parsing using bidirectional lstm feature representations. Transactions of the Association for Computational Linguistics, 4:313–327.
- What do recurrent neural network grammars learn about syntax? arXiv preprint arXiv:1611.05774.
- A diversity-promoting objective function for neural conversation models. arXiv:abs/1510.03055.
- Empdg: Multiresolution interactive empathetic dialogue generation. arXiv:abs/1911.08698.
- Knowledge bridging for empathetic dialogue generation. In AAAI.
- Infusing multi-source knowledge with heterogeneous graph neural network for emotional conversation generation. In AAAI, volume 35, pages 13343–13352.
- Moel: Mixture of empathetic listeners. In EMNLP-IJCNLP, page 121–132.
- Towards emotional support dialog systems. arXiv:abs/2106.01144.
- Mime: Mimicking emotions for empathetic response generation. In EMNLP, page 8968–8979.
- Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
- Saif Mohammad. 2018. Obtaining reliable human ratings of valence, arousal, and dominance for 20,000 english words. In ACL, pages 174–184.
- Saif M Mohammad and Peter D Turney. 2013. Crowdsourcing a word–emotion association lexicon. Computational intelligence, 29(3):436–465.
- Meredith Osmond. 1997. The prepositions we use in the construal of emotion: Why do we say fed up with but sick and tired of. The language of emotions: Conceptualization, expression, and theoretical foundation, 21:111.
- Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543.
- Günter Radden. 1998. The conceptualisation of emotional causality by means of prepositional phrases. Speaking of emotions: Conceptualisation and expression, pages 273–294.
- Towards empathetic open-domain conversation models: A new benchmark and dataset. In ACL, page 5370–5381.
- Cem: Commonsense-aware empathetic response generation. In Proceedings of the AAAI Conference on Artificial Intelligence, Virginia, USA. AAAI Press.
- Attention is all you need. In NeurIPS, page 5998–6008.
- Cass: Towards building a social-support chatbot for online health community. In PACMHCI, volume 5, pages 1–31.
- Comae: A multi-factor hierarchical framework for empathetic response generation. In ACL.
- Care: Commonsense-aware emotional response generation with latent concepts. In AAAI, volume 35, pages 14577–14585.
- Towards persona-based empathetic conversational models. arXiv:abs/2004.12316.
- Zhou Yang (82 papers)
- Zhaochun Ren (117 papers)
- Yufeng Wang (43 papers)
- Xiaofei Zhu (16 papers)
- Zhihao Chen (65 papers)
- Tiecheng Cai (1 paper)
- Yunbing Wu (2 papers)
- Yisong Su (3 papers)
- Sibo Ju (3 papers)
- Xiangwen Liao (8 papers)