TERG: Topic-Aware Emotional Response Generation for Chatbot

Huo, Pei; Yang, Yan; Zhou, Jie; Chen, Chengcai; He, Liang

doi:10.1109/ijcnn48605.2020.9206719

Cited by 8 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They were invited to experience a simulated conversation with a chatbot designed by a group of Ph.D. students. A set of emotion words generated for a chatbot was selected from Huo et al ( 2020 ), which included words like “sorry,” “like,” “truly,” “thank you,” and “pity” ( Supplementary Table 1 ).…”

Section: Methodsmentioning

confidence: 99%

The Effects of Chatbot Service Recovery With Emotion Words on Customer Satisfaction, Repurchase Intention, and Positive Word-Of-Mouth

Yun

Park

2022

Front. Psychol.

View full text Add to dashboard Cite

This study sought to examine the effect of the quality of chatbot services on customer satisfaction, repurchase intention, and positive word-of-mouth by comparing two groups, namely chatbots with and without emotion words. An online survey was conducted for 2 weeks in May 2021. A total of 380 responses were collected and analyzed using structural equation modeling to test the hypothesis. The theoretical basis of the study was the SERVQUAL theory, which is widely used in measuring and managing service quality in various industries. The results showed that the assurance and reliability of chatbots positively impact customer satisfaction for both groups. However, empathy and interactivity positively affect customer satisfaction only for chatbots with emotion words. Responsiveness did not have an impact on customer satisfaction for both groups. Customer satisfaction positively impacts repurchase intention and positive word-of-mouth for both groups. The findings of this study can serve as a priori research to empirically prove the effectiveness of chatbots with emotion words.

show abstract

Section: Methodsmentioning

confidence: 99%

The Effects of Chatbot Service Recovery With Emotion Words on Customer Satisfaction, Repurchase Intention, and Positive Word-Of-Mouth

Yun

Park

2022

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…The authors of (Saha et al, 2020a) demonstrated how reinforcement learning may be used to generate meaningful responses while training generation frameworks. In (Saha et al, 2020b(Saha et al, , 2021a, the authors show how subtleties in human communication, such as Apart from these, several other work (Wei et al, 2019;Ide and Kawahara, 2021;Huo et al, 2020) that suggests using sentiment and/or emotion as an additional input in generation frameworks either during decoding or as reward to guide the models for generating responses aligned with the user's mood or feelings.…”

Section: Related Workmentioning

confidence: 99%

A Shoulder to Cry on: Towards A Motivational Virtual Assistant for Assuaging Mental Agony

Saha¹,

Reddy²,

Das³

et al. 2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Mental Health Disorders continue plaguing humans worldwide. Aggravating this situation is the severe shortage of qualified and competent mental health professionals (MHPs), which underlines the need for developing Virtual Assistants (VAs) that can assist MHPs. The data+ML for automation can come from platforms that allow visiting and posting messages in peerto-peer anonymous manner for sharing their experiences (frequently stigmatized) and seeking support. In this paper, we propose a VA that can act as the first point of contact and comfort for mental health patients. We curate a dataset, Motivational VA: MotiVAte comprising of 7k dyadic conversations collected from a peer-topeer support platform. The system employs two mechanisms: (i) Mental Illness Classification: an attention based BERT classifier that outputs the mental disorder category out of the 4 categories, viz., Major Depressive Disorder (MDD), Anxiety, Obsessive Compulsive Disorder (OCD) and Post-traumatic Stress Disorder (PTSD), based on the input ongoing dialog between the support seeker and the VA; and (ii) Mental Illness Conditioned Motivational Dialogue Generation (MI-MDG): a sentiment driven Reinforcement Learning (RL) based motivational response generator. The empirical evaluation demonstrates the system capability by way of outperforming several baselines.

show abstract

“…Most of previous works for topic-aware dialogue system (Xing et al, 2017;Dziri et al, 2019;Yang et al, 2019;Huo et al, 2020) utilize attention mechanism on all topics at the decode stage to bias the generation probability. Tang et al (2019) proposes a structured approach that introduces coarse-grained keywords to control the intended content of system responses and Xu, Zhao, and Zhang (2020) proposes Topic-Aware Dual-attention Matching (TADAM) Network to select suitable response but all of their systems are retrieval-based.…”

Section: Related Work Topic-aware Dialogue Systemmentioning

confidence: 99%

“…Other works cast this task as a pipeline system, predict the keywords, then capture the topic, and finally retrieve corresponding response Zhou et al, 2020). Another line of work focuses on single-turn topic-aware response generation conditioned on previously given topics (Feng et al, 2018;Yang et al, 2019;Huo et al, 2020). All these methods fall short in two ways.…”

Section: Introductionmentioning

confidence: 99%

TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System

Wang,

Cui,

Zhou

et al. 2021

Preprint

View full text Add to dashboard Cite

A multi-turn dialogue always follows a specific topic thread, and topic shift at the discourse level occurs naturally as the conversation progresses, necessitating the model's ability to capture different topics and generate topic-aware responses. Previous research has either predicted the topic first and then generated the relevant response, or simply applied the attention mechanism to all topics, ignoring the joint distribution of the topic prediction and response generation models and resulting in uncontrollable and unrelated responses. In this paper, we propose a joint framework with a topic refinement mechanism to learn these two tasks simultaneously. Specifically, we design a three-pass iteration mechanism to generate coarse response first, then predict corresponding topics, and finally generate refined response conditioned on predicted topics. Moreover, we utilize GPT2DoubleHeads and BERT for the topic prediction task respectively, aiming to investigate the effects of joint learning and the understanding ability of GPT model. Experimental results demonstrate that our proposed framework achieves new state-of-the-art performance at response generation task and the great potential understanding capability of GPT model.

show abstract

TERG: Topic-Aware Emotional Response Generation for Chatbot

Cited by 8 publications

References 13 publications

The Effects of Chatbot Service Recovery With Emotion Words on Customer Satisfaction, Repurchase Intention, and Positive Word-Of-Mouth

The Effects of Chatbot Service Recovery With Emotion Words on Customer Satisfaction, Repurchase Intention, and Positive Word-Of-Mouth

A Shoulder to Cry on: Towards A Motivational Virtual Assistant for Assuaging Mental Agony

TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System

Contact Info

Product

Resources

About