Generating Empathetic Responses by Looking Ahead the User’s Sentiment

@article{Shin2019GeneratingER,
  title={Generating Empathetic Responses by Looking Ahead the User’s Sentiment},
  author={Jamin Shin and Peng Xu and Andrea Madotto and Pascale Fung},
  journal={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2019},
  pages={7989-7993}
}
  • Jamin ShinPeng Xu Pascale Fung
  • Published 20 June 2019
  • Computer Science
  • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
An important aspect of human conversation difficult for machines is conversing with empathy, which is to understand the user’s emotion and respond appropriately. Recent neural conversation models that attempted to generate empathetic responses either focused on conditioning the output to a given emotion, or incorporating the current user emotional state. However, these approaches do not factor in how the user would feel towards the generated response. Hence, in this paper, we propose Sentiment… 
[PDF] Semantic Reader
21 Citations
Highly Influential Citations
2
Background Citations
16
Methods Citations
4
Results Citations
1

Figures and Tables from this paper

21 Citations

Generating Empathetic Responses with a Large Scale Dialog Dataset

This paper describes in detail the curation process of a large-scale dialog dataset where each utterance is labeled with one of 32 emotions and 9 intent categories and shows how to build a multi-turn empathetic dialog model that performs well compared to its baselines over 6,000 human evaluated instances.

MIME: MIMicking Emotions for Empathetic Response Generation

This work argues that empathetic responses often mimic the emotion of the user to a varying degree, depending on its positivity or negativity and content, and introduces stochasticity into the emotion mixture that yields emotionally more varied emPathetic responses than the previous work.

Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations

A novel framework is proposed that improves empathetic response generation by recognizing emotion cause in conversations and incorporating emotion cause information improves the performance of the model on both emotion recognition and response generation.

Empathetic Dialog Generation with Fine-Grained Intents

This paper describes how to incorporate a taxonomy of 32 emotion categories and 8 additional emotion regulating intents to succeed the task of empathetic response generation and evaluated and demonstrated how this model produces more emPathetic dialogs compared with its baselines.

Using Extracted Emotion Cause to Improve Content-Relevance for Empathetic Conversation Generation

Experimental results indicate that the proposed emotion cause extractor improves recall scores markedly compared to the baselines, and the proposed empathetic conversation generator has superior performance and improves the content-relevance of generated responses.

EmoDM: Empathetic Response Generation with Emotion-aware Dialogue Management

A novel empathetic response generation model with emotion-aware dialogue management that predicts a target emotion and a user’s intent based on the results of the emotion state tracking and is used to guide the generation of responses.

Empathy-driven Arabic Conversational Chatbot

This work creates an Arabic conversational dataset that comprises empathetic responses and proposes a special encoder-decoder composed of a Long Short-Term Memory (LSTM) Sequence-to-Sequence (Seq2Seq) with Attention to address the limitation of data scale.

Exemplars-Guided Empathetic Response Generation Controlled by the Elements of Human Communication

Three elements of human communication—emotional presence, interpretation, and exploration—and sentiment are additionally introduced using synthetic labels to guide the generation towards empathy and it is empirically shown that these approaches yield significant improvements in empathetic response quality in terms of both automated and human-evaluated metrics.

Multi-Party Empathetic Dialogue Generation: A New Task for Dialog Systems

Empathetic dialogue assembles emotion understanding, feeling projection, and appropriate response generation. Existing work for empathetic dialogue generation concentrates on the two-party…

Towards Detecting Need for Empathetic Response in Motivational Interviewing

This position paper proposes to leverage pre-trained language models and empathy-related general conversation corpora in a unique labeller-detector framework, where the labeller automatically annotates a motivational interviewing conversation corpus with empathy labels to train the detector that determines the need for therapist empathy.

References

SHOWING 1-10 OF 29 REFERENCES

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.

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.

Eliciting Positive Emotion through Affect-Sensitive Dialogue Response Generation: A Neural Network Approach

This paper builds a fully data driven chat-oriented dialogue system that can dynamically mimic affective human interactions by utilizing a neural network architecture and proposes a sequence-to-sequence response generator that considers the emotional context of the dialogue.

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.

Deep Reinforcement Learning for Dialogue Generation

This work simulates dialogues between two virtual agents, using policy gradient methods to reward sequences that display three useful conversational properties: informativity, non-repetitive turns, coherence, and ease of answering.

A Diversity-Promoting Objective Function for Neural Conversation Models

This work proposes using Maximum Mutual Information (MMI) as the objective function in neural models, and demonstrates that the proposed MMI models produce more diverse, interesting, and appropriate responses, yielding substantive gains in BLEU scores on two conversational datasets and in human evaluations.

A Neural Conversational Model

A simple approach to conversational modeling which uses the recently proposed sequence to sequence framework, and is able to extract knowledge from both a domain specific dataset, and from a large, noisy, and general domain dataset of movie subtitles.

Recognizing, Modeling, and Responding to Users' Affective States

It is demonstrated that empathic feedback of an agent may reduce user arousal while hearing interviewer questions, which may prove useful for educational systems or applications that induce user stress.

Hierarchical Neural Story Generation

This work collects a large dataset of 300K human-written stories paired with writing prompts from an online forum that enables hierarchical story generation, where the model first generates a premise, and then transforms it into a passage of text.

Affect Listeners: Acquisition of Affective States by Means of Conversational Systems

  • M. Skowron
  • Computer Science
    COST 2102 Training School
  • 2009
The system architecture and the initial set of core components and mechanisms applied are described, and the application and evaluation scenarios of Affect Listener systems are discussed.