Generating emotional response by conditional variational auto-encoder in open-domain dialogue system

Liu, Mengjuan; Bao, Xiaoming; Liu, Jiang; Zhao, Pei; Shen, Yuchen

doi:10.1016/j.neucom.2021.07.007

Cited by 15 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to this model, research has shown that the Conditional Variational Autoencoder (CVAE) model can also improve the diversity of responses. In CVAE, a latent variable is used to learn a distribution over possible conversational intents, and greedy decoders are used to generate responses [36].…”

Section: Deep Learning In Chatbotmentioning

confidence: 99%

“…Their model uses a latent space variable and six emotion categories to generate multiple responses that generate multiple emotionally consistent responses. Similarly, Liu et al [36] also generate several responses and select the most appropriate one based on grammar, meaning, and emotional score. Zhang et al [53] argued that an intervention mechanism is needed to improve response diversity.…”

Section: Rq2: What Problems Are Addressed In the Chatbotmentioning

confidence: 99%

“…To that effect, some studies predict the emotion by applying the principle of Valence and Arousal (VA) to embed affective meaning for each word in the input message [47,62,63]. Other studies built on the previous work and embedded each input word with a three-dimensional emotion embedding based on Valence, Arousal, and Dominance (VAD) [38] to achieve a more 10 Human Behavior and Emerging Technologies fine-grained emotion detection [36,39,51,64,65]. Li et al [66,67] argue that words in messages are usually connected and show that capturing the connections of words enables a deeper understanding of the user's emotion.…”

Section: Poor Emotion Capturementioning

confidence: 99%

See 2 more Smart Citations

Emotionally Intelligent Chatbots: A Systematic Literature Review

Bilquise

Ibrahim

Shaalan

2022

Human Behavior and Emerging Technologies

View full text Add to dashboard Cite

Conversational technologies are transforming the landscape of human-machine interaction. Chatbots are increasingly being used in several domains to substitute human agents in performing tasks, answering questions, giving advice, and providing social and emotional support. Therefore, improving user satisfaction with these technologies is imperative for their successful integration. Researchers are leveraging Artificial Intelligence (AI) and Natural Language Processing (NLP) techniques to impart emotional intelligence capabilities in chatbots. This study provides a systematic review of research on developing emotionally intelligent chatbots. We employ a systematic approach to gather and analyze 42 articles published in the last decade. The review is aimed at providing a comprehensive analysis of past research to discover the problems addressed, the techniques used, and the evaluation measures employed by studies in embedding emotion in chatbot conversations. The study’s findings reveal that most studies are based on an open-domain generative chatbot architecture. Researchers mainly address the issue of accurately detecting the user’s emotion and generating emotionally relevant responses. Nearly 57% of the studies use an enhanced Seq2Seq encoding and decoding of the input of the conversational model. Almost all the studies use both the automatic and manual evaluation measures to evaluate the chatbots, with the BLEU measure being the most popular method for objective evaluation.

show abstract

Section: Deep Learning In Chatbotmentioning

confidence: 99%

Section: Rq2: What Problems Are Addressed In the Chatbotmentioning

confidence: 99%

Section: Poor Emotion Capturementioning

confidence: 99%

See 1 more Smart Citation

Emotionally Intelligent Chatbots: A Systematic Literature Review

Bilquise

Ibrahim

Shaalan

2022

Human Behavior and Emerging Technologies

View full text Add to dashboard Cite

show abstract

“…This information is then used in the response generation process to produce an affect-sensitive response that elicits positive emotion. Liu et al [32] feed the semantic vector of each word with its affective vector together into the conditional variational autoencoder model, enabling the model to learn the response's affective distributions, thereby predict an appropriate emotion for response generation. Li et al [33] propose a fully data-driven interactive double states emotion cell model (IDS-ECM), which has two layers.…”

Section: Emotion Predictionmentioning

confidence: 99%

SAEP: A Surrounding-Aware Individual Emotion Prediction Model Combined with T-LSTM and Memory Attention Mechanism

Wang

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

The future emotion prediction of users on social media has been attracting increasing attention from academics. Previous studies on predicting future emotion have focused on the characteristics of individuals’ emotion changes; however, the role of the individual’s neighbors has not yet been thoroughly researched. To fill this gap, a surrounding-aware individual emotion prediction model (SAEP) based on a deep encoder–decoder architecture is proposed to predict individuals’ future emotions. In particular, two memory-based attention networks are constructed: The time-evolving attention network and the surrounding attention network to extract the features of the emotional changes of users and neighbors, respectively. Then, these features are incorporated into the emotion prediction task. In addition, a novel variant LSTM is introduced as the encoder of the proposed model, which can effectively extract complex patterns of users’ emotional changes from irregular time series. Extensive experimental results show that the proposed approach outperforms five alternative methods. The SAEP approach has improved by approximately 4.21–14.84% micro F1 on a dataset built from Twitter and 7.30–13.41% on a dataset built from Microblog. Further analyses validate the effectiveness of the proposed time-evolving context and surrounding context, as well as the factors that may affect the prediction results.

show abstract

“…Latent variable models such as the Variational Auto Encoder (VAE) (Kingma and Welling, 2014) and the Conditional Variational Auto Encoder (CVAE) (Sohn et al, 2015) have been applied to the task of open-domain dialogue generation, where the potential dialogue responses are modelled as a latent Gaussian distribution (Li et al, 2020;Shen et al, 2018;Zhao et al, 2017;Serban et al, 2017). In addition to personalized dialogue generation (examples provided in the introduction), CVAEs have been applied to conditional dialogue generation tasks such as emotional dialogue generation (Liu et al, 2021;As-ghar et al, 2020;Zhou and Wang, 2018) as well as topical dialogue generation (Wang et al, 2020).…”

Section: Latent Variable Modelsmentioning

confidence: 99%

DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation

Lee¹,

Lee²,

Gan³

2021

Preprint

View full text Add to dashboard Cite

The generation of personalized dialogue is vital to natural and human-like conversation. Typically, personalized dialogue generation models involve conditioning the generated response on the dialogue history and a representation of the persona/personality of the interlocutor. As it is impractical to obtain the persona/personality representations for every interlocutor, recent works have explored the possibility of generating personalized dialogue by finetuning the model with dialogue examples corresponding to a given persona instead. However, in real-world implementations, a sufficient number of corresponding dialogue examples are also rarely available. Hence, in this paper, we propose a Dual Latent Variable Generator (DLVGen) capable of generating personalized dialogue in the absence of any persona/personality information or any corresponding dialogue examples. Unlike prior work, DLVGen models the latent distribution over potential responses as well as the latent distribution over the agent's potential persona. During inference, latent variables are sampled from both distributions and fed into the decoder. Empirical results show that DLVGen is capable of generating diverse responses which accurately incorporate the agent's persona.

show abstract

Generating emotional response by conditional variational auto-encoder in open-domain dialogue system

Cited by 15 publications

References 16 publications

Emotionally Intelligent Chatbots: A Systematic Literature Review

Emotionally Intelligent Chatbots: A Systematic Literature Review

SAEP: A Surrounding-Aware Individual Emotion Prediction Model Combined with T-LSTM and Memory Attention Mechanism

DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation

Contact Info

Product

Resources

About