Towards Emotional Support Dialog Systems

@article{Liu2021TowardsES,
  title={Towards Emotional Support Dialog Systems},
  author={Siyang Liu and Chujie Zheng and Orianna Demasi and Sahand Sabour and Yu Li and Zhou Yu and Yong Jiang and Minlie Huang},
  journal={ArXiv},
  year={2021},
  volume={abs/2106.01144}
}
Emotional support is a crucial ability for many conversation scenarios, including social interactions, mental health support, and customer service chats. Following reasonable procedures and using various support skills can help to effectively provide support. However, due to the lack of a well-designed task and corpora of effective emotional support conversations, research on building emotional support into dialog systems remains lacking. In this paper, we define the Emotional Support… 

PoKE: Prior Knowledge Enhanced Emotional Support Conversation with Latent Variable

The proposed PoKE model fully taps the potential of prior knowledge in terms of exemplars and strategy sequence and then utilizes a latent variable to model the one-to-many relationship of strategy, and demonstrates the superiority and diversity of PoKE.

PAL: Persona-Augmented Emotional Support Conversation Generation

Automatic and manual evaluations demonstrate that the proposed model, PAL, achieves state-of-the-art results, outperforming the baselines on the studied benchmark.

Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning

A novel system named MultiESC, which focuses on capturing users’ subtle emotional expressions and understanding their emotion causes, and proposes lookahead heuristics to estimate the future user feedback after using particular strategies, which helps to select strategies that can lead to the best long-term effects.

AugESC: Large-scale Data Augmentation for Emotional Support Conversation with Pre-trained Language Models

This paper proposes exploiting large-scale pre-trained language models for data augmentation, and demonstrates with interactive evaluation that AUGESC can further enhance dialog models tuned on ESConv to handle various conversation topics and to provide significantly more effective emotional support.

FADO: Feedback-Aware Double COntrolling Network for Emotional Support Conversation

Experimental results on ESConv show that the proposed FADO has achieved the state-of-the-art performance in terms of both strategy selection and response generation.

MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation

A novel model is proposed, which firstly infers the user’s fine-grained emotional status, and then responds skillfully using a mixture of strategy, which reveals the benefits of fine- grained emotion understanding as well as mixed-up strategy modeling.

Chatbots for Mental Health Support: Exploring the Impact of Emohaa on Reducing Mental Distress in China

The growing demand for mental health support has highlighted the importance of conversational agents as human supporters worldwide and in China. These agents could increase availability and reduce

Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation

A two-stage conversational agent is proposed for the generation of emotional dialogue that outperforms the compared models in the emotion generation and maintains the semantic performance in the automatic and human evaluations.

Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection

A Serial Encoding and Emotion-Knowledge interaction (SEEK) method for empathetic dialogue generation that uses a more sensitive encoding strategy which is more sensitive to the emotion dynamics in the conversations to predict the emotion-intent characteristic of response.

D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat

In a depression-diagnosis-directed clinical session, doctors initiate a conversation with ample emotional support that guides the patients to expose their symptoms based on clinical diagnosis

References

SHOWING 1-10 OF 42 REFERENCES

A BDI Dialogue Agent for Social Support: Specification and Evaluation Method

An evaluation method is proposed based on multi-stage expert evaluation in which (adult) online bullying counselors interact with the system with varying degrees of freedom and children will be involved in multiple stages and under the supervision of experts.

A Conversation Model Enabling Intelligent Agents to Give Emotional Support

A domain-independent conversational model is proposed that is based on topics suggested by cognitive appraisal theories of emotion and the 5-phase model that is used to structure online counseling conversations and implemented in an embodied conversational agent called Robin.

Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset

This work proposes a new benchmark for empathetic dialogue generation and EmpatheticDialogues, a novel dataset of 25k conversations grounded in emotional situations, and presents empirical comparisons of dialogue model adaptations forEmpathetic responding, leveraging existing models or datasets without requiring lengthy re-training of the full model.

Challenges in Building Intelligent Open-domain Dialog Systems

This article reviews the recent work on neural approaches that are devoted to addressing three challenges in developing intelligent open-domain dialog systems: semantics, consistency, and interactiveness.

Emotional Dialogue Generation using Image-Grounded Language Models

This work presents the first example of an image-grounded conversational agent using visual sentiment, facial expression and scene features, and shows that key qualities of the generated dialogue can be manipulated by the features used for training the agent.

MojiTalk: Generating Emotional Responses at Scale

This paper collects a large corpus of Twitter conversations that include emojis in the response and investigates several conditional variational autoencoders training on these conversations, which allow us to use emojes to control the emotion of the generated text.

Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

This paper proposes Emotional Chatting Machine (ECM), the first work that addresses the emotion factor in large-scale conversation generation using three new mechanisms that respectively models the high-level abstraction of emotion expressions by embedding emotion categories.

A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Support

A novel unifying theoretically-grounded framework for characterizing the communication of empathy in text-based conversations is developed and a multi-task RoBERTa-based bi-encoder model for identifying empathy in conversations and extracting rationales underlying its predictions is developed.

MoEL: Mixture of Empathetic Listeners

A novel end-to-end approach for modeling empathy in dialogue systems: Mixture of Empathetic Listeners (MoEL), which outperforms multitask training baseline in terms of empathy, relevance, and fluency.

Using Crowdsourcing for the Development of Online Emotional Support Agents

This paper presents an empirical study that was conducted with the aim to investigate how people help each other to cope with stressful situations via online social networks.