TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Perspective-taking and Pragmatics for Generating Empatheti...

Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes

Hyunwoo Kim, Byeongchang Kim, Gunhee Kim

2021-09-18EMNLP 2021 11Recognizing Emotion Cause in ConversationsDialogue GenerationEmotion RecognitionResponse GenerationEmpathetic Response Generation
PaperPDFCode(official)

Abstract

Empathy is a complex cognitive ability based on the reasoning of others' affective states. In order to better understand others and express stronger empathy in dialogues, 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. However, previous approaches for recognizing emotion cause words in text require sub-utterance level annotations, which can be demanding. Taking inspiration from social cognition, we leverage a generative estimator to infer emotion cause words from utterances with no word-level label. Also, we introduce a novel method based on pragmatics to make dialogue models focus on targeted words in the input during generation. Our method is applicable to any dialogue models with no additional training on the fly. We show our approach improves multiple best-performing dialogue agents on generating more focused empathetic responses in terms of both automatic and human evaluation.

Results

TaskDatasetMetricValueModel
Recognizing Emotion Cause in ConversationsEmoCauseTop-1 Recall41.3Human
Recognizing Emotion Cause in ConversationsEmoCauseTop-3 Recall81.1Human
Recognizing Emotion Cause in ConversationsEmoCauseTop-5 Recall95Human
Recognizing Emotion Cause in ConversationsEmoCauseTop-1 Recall17.3GEE
Recognizing Emotion Cause in ConversationsEmoCauseTop-3 Recall48.1GEE
Recognizing Emotion Cause in ConversationsEmoCauseTop-5 Recall68.4GEE
Recognizing Emotion Cause in ConversationsEmoCauseTop-1 Recall13.8BERT-Attention
Recognizing Emotion Cause in ConversationsEmoCauseTop-3 Recall40.6BERT-Attention
Recognizing Emotion Cause in ConversationsEmoCauseTop-5 Recall61.2BERT-Attention
Recognizing Emotion Cause in ConversationsEmoCauseTop-1 Recall13.4EmpDG
Recognizing Emotion Cause in ConversationsEmoCauseTop-3 Recall36.2EmpDG
Recognizing Emotion Cause in ConversationsEmoCauseTop-5 Recall49.3EmpDG
Recognizing Emotion Cause in ConversationsEmoCauseTop-1 Recall12.7RAKE
Recognizing Emotion Cause in ConversationsEmoCauseTop-3 Recall35.8RAKE
Recognizing Emotion Cause in ConversationsEmoCauseTop-5 Recall55RAKE
Recognizing Emotion Cause in ConversationsEmoCauseTop-1 Recall10.7Random
Recognizing Emotion Cause in ConversationsEmoCauseTop-3 Recall30.6Random
Recognizing Emotion Cause in ConversationsEmoCauseTop-5 Recall48.5Random

Related Papers

Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation2025-07-21Emotional Support with LLM-based Empathetic Dialogue Generation2025-07-17Camera-based implicit mind reading by capturing higher-order semantic dynamics of human gaze within environmental context2025-07-17A Robust Incomplete Multimodal Low-Rank Adaptation Approach for Emotion Recognition2025-07-15ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching2025-07-12Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation2025-07-11CAST-Phys: Contactless Affective States Through Physiological signals Database2025-07-08Exploring Remote Physiological Signal Measurement under Dynamic Lighting Conditions at Night: Dataset, Experiment, and Analysis2025-07-06