Generating Empathetic Responses with a Large Scale Dialog Dataset

• URL: http://arxiv.org/abs/2105.06829v1
• Date: Fri, 14 May 2021 13:45:40 GMT
• Title: Generating Empathetic Responses with a Large Scale Dialog Dataset
• Authors: Yubo Xie, Pearl Pu
• Abstract summary: 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.
• Score: 0.76146285961466
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The task of empathetic response generation aims at generating syntactically correct and, more importantly, emotionally appropriate responses following previous dialog turns. Existing models either directly incorporate pre-defined emotion information to guide the response generation, or use deterministic rules to decide the response emotion, ignoring the subtle emotion interactions captured in human conversations. With the advent of advanced language models, it is possible to learn the nuanced emotional exchanges captured in natural language dialogs. To fully explore the range of emotions and dialog intents, it is important to curate a dataset large enough to shed light on the general understanding of human emotional interactions in our conversations. In this paper, we describe 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. We then show how to build a multi-turn empathetic dialog model that performs well compared to its baselines over 6,000 human evaluated instances.

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)
• Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling [50.99252242917458]
  Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. To address the issue of data scarcity, we meticulously create emotional labels in terms of category and intensity. Our model outperforms the baseline models in understanding and rendering emotions.
  arXiv  Detail & Related papers  (2023-12-19T08:47:50Z)
• 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)
• Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations [31.707018753687098]
  We introduce Affective Visual Dialog as a testbed for research on understanding the formation of emotions in visually grounded conversations. The task involves three skills: Dialog-based Question Answering, Dialog-based Emotion Prediction and Affective emotion explanation generation. Our key contribution is the collection of a large-scale dataset, dubbed AffectVisDial, consisting of 50K 10-turn visually grounded dialogs.
  arXiv  Detail & Related papers  (2023-08-30T22:50:32Z)
• Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation [16.659457455269127]
  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.
  arXiv  Detail & Related papers  (2023-01-12T10:03:56Z)
• Empathetic Response Generation with State Management [32.421924357260075]
  The goal of empathetic response generation is to enhance the ability of dialogue systems to perceive and express emotions in conversations. We propose a novel empathetic response generation model that can consider multiple state information including emotions and intents simultaneously. Experimental results show that dynamically managing different information can help the model generate more empathetic responses.
  arXiv  Detail & Related papers  (2022-05-07T16:17:28Z)
• 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)
• 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)
• EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion in Task-Oriented Dialogue Systems [3.3010169113961325]
  EmoWOZ is a large-scale manually emotion-annotated corpus of task-oriented dialogues. It contains more than 11K dialogues with more than 83K emotion annotations of user utterances. We propose a novel emotion labelling scheme, which is tailored to task-oriented dialogues.
  arXiv  Detail & Related papers  (2021-09-10T15:00:01Z)
• 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)
• A Taxonomy of Empathetic Response Intents in Human Social Conversations [1.52292571922932]
  Open-domain conversational agents are becoming increasingly popular in the natural language processing community. One of the challenges is enabling them to converse in an empathetic manner. Current neural response generation methods rely solely on end-to-end learning from large scale conversation data to generate dialogues. Recent work has shown the promise of combining dialogue act/intent modelling and neural response generation.
  arXiv  Detail & Related papers  (2020-12-07T21:56:45Z)

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.