Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation
- URL: http://arxiv.org/abs/2301.04907v3
- Date: Tue, 01 Oct 2024 10:36:20 GMT
- Title: Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation
- Authors: Yushan Qian, Bo Wang, Shangzhao Ma, Wu Bin, Shuo Zhang, Dongming Zhao, Kun Huang, Yuexian Hou,
- Abstract summary: We propose a two-stage conversational agent for the generation of emotional dialogue.
First, a dialogue model trained without the emotion-annotated dialogue corpus generates a prototype response that meets the contextual semantics.
Secondly, the first-stage prototype is modified by a controllable emotion refiner with the empathy hypothesis.
- Score: 16.659457455269127
- License:
- Abstract: Towards human-like dialogue systems, current emotional dialogue approaches jointly model emotion and semantics with a unified neural network. This strategy tends to generate safe responses due to the mutual restriction between emotion and semantics, and requires rare emotion-annotated large-scale dialogue corpus. Inspired by the "think twice" behavior in human dialogue, we propose a two-stage conversational agent for the generation of emotional dialogue. Firstly, a dialogue model trained without the emotion-annotated dialogue corpus generates a prototype response that meets the contextual semantics. Secondly, the first-stage prototype is modified by a controllable emotion refiner with the empathy hypothesis. Experimental results on the DailyDialog and EmpatheticDialogues datasets demonstrate that the proposed conversational outperforms the comparison models in emotion generation and maintains the semantic performance in automatic and human evaluations.
Related papers
- Personality-affected Emotion Generation in Dialog Systems [67.40609683389947]
We propose a new task, Personality-affected Emotion Generation, to generate emotion based on the personality given to the dialog system.
We analyze the challenges in this task, i.e., (1) heterogeneously integrating personality and emotional factors and (2) extracting multi-granularity emotional information in the dialog context.
Results suggest that by adopting our method, the emotion generation performance is improved by 13% in macro-F1 and 5% in weighted-F1 from the BERT-base model.
arXiv Detail & Related papers (2024-04-03T08:48:50Z) - Dynamic Causal Disentanglement Model for Dialogue Emotion Detection [77.96255121683011]
We propose a Dynamic Causal Disentanglement Model based on hidden variable separation.
This model effectively decomposes the content of dialogues and investigates the temporal accumulation of emotions.
Specifically, we propose a dynamic temporal disentanglement model to infer the propagation of utterances and hidden variables.
arXiv Detail & Related papers (2023-09-13T12:58:09Z) - Empathetic Dialogue Generation via Sensitive Emotion Recognition and
Sensible Knowledge Selection [47.60224978460442]
We propose a Serial and Emotion-Knowledge interaction (SEEK) method for empathetic dialogue generation.
We use a fine-grained encoding strategy which is more sensitive to the emotion dynamics (emotion flow) in the conversations to predict the emotion-intent characteristic of response. Besides, we design a novel framework to model the interaction between knowledge and emotion to generate more sensible response.
arXiv Detail & Related papers (2022-10-21T03:51:18Z) - Building a Dialogue Corpus Annotated with Expressed and Experienced
Emotions [12.29324895944564]
In communication, a human would recognize the emotion of an interlocutor and respond with an appropriate emotion, such as empathy and comfort.
We propose a method to build a dialogue corpus annotated with two kinds of emotions.
We collect dialogues from Twitter and annotate each utterance with the emotion that a speaker put into the utterance (expressed emotion) and the emotion that a listener felt after listening to the utterance (experienced emotion)
arXiv Detail & Related papers (2022-05-24T07:40:11Z) - Chat-Capsule: A Hierarchical Capsule for Dialog-level Emotion Analysis [70.98130990040228]
We propose a Context-based Hierarchical Attention Capsule(Chat-Capsule) model, which models both utterance-level and dialog-level emotions and their interrelations.
On a dialog dataset collected from customer support of an e-commerce platform, our model is also able to predict user satisfaction and emotion curve category.
arXiv Detail & Related papers (2022-03-23T08:04:30Z) - Simulated Annealing for Emotional Dialogue Systems [22.96717845092991]
We consider the task of expressing a specific emotion for dialogue generation.
Our proposed method shows 12% improvements in emotion accuracy compared with the previous state-of-the-art method.
arXiv Detail & Related papers (2021-09-22T13:17:17Z) - Perspective-taking and Pragmatics for Generating Empathetic Responses
Focused on Emotion Causes [50.569762345799354]
We argue that two issues must be tackled at the same time: (i) identifying which word is the cause for the other's emotion from his or her utterance and (ii) reflecting those specific words in the response generation.
Taking inspiration from social cognition, we leverage a generative estimator to infer emotion cause words from utterances with no word-level label.
arXiv Detail & Related papers (2021-09-18T04:22:49Z) - Constructing Emotion Consensus and Utilizing Unpaired Data for
Empathetic Dialogue Generation [22.2430593119389]
We propose a dual-generative model, Dual-Emp, to simultaneously construct the emotion consensus and utilize some external unpaired data.
Our method outperforms competitive baselines in producing coherent and empathetic responses.
arXiv Detail & Related papers (2021-09-16T07:57:01Z) - Emotion-aware Chat Machine: Automatic Emotional Response Generation for
Human-like Emotional Interaction [55.47134146639492]
This article proposes a unifed end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post.
Experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness.
arXiv Detail & Related papers (2021-06-06T06:26:15Z) - Generating Empathetic Responses with a Large Scale Dialog Dataset [0.76146285961466]
Existing models either directly incorporate pre-defined emotion information to guide the response generation, or use deterministic rules to decide the response emotion.
We show how to build a multi-turn empathetic dialog model that performs well compared to its baselines over 6,000 human evaluated instances.
arXiv Detail & Related papers (2021-05-14T13:45:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.