natural-language-processing-7

Empathetic Response Generation

3260 papers • 126 benchmarks • 313 datasets

Generate empathetic responses in dialogues

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in empathetic-response-generation-14

Trend

Dataset

Best Model

Actions

EmpatheticDialogues

Libraries

i

Use these libraries to find empathetic-response-generation-14 models and implementations

Datasets

EmpatheticDialogues

StickerConv

Subtasks

No subtasks available.

Most implemented papers

MIME: MIMicking Emotions for Empathetic Response Generation

Soujanya Poria, Navonil Majumder, Deepanway Ghosal, Pengfei Hong, Rada Mihalcea, Alexander Gelbukh, Shanshan Peng, Jiankun Lu•Sat Oct 03 2020

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.

231

Content

0

Paper Graph

Empathetic BERT2BERT Conversational Model: Learning Arabic Language Generation with Little Data

Hazem M. Hajj, Wissam Antoun, Tarek Naous, Reem A. Mahmoud•Sat Mar 06 2021

A transformer-based encoder-decoder initialized with AraBERT parameters is proposed, validating its high capability in exhibiting empathy while generating relevant and fluent responses in open-domain settings.

20 0

Paper Graph

Empathetic Dialog Generation with Fine-Grained Intents

Yubo Xie, P. Pu•Thu May 13 2021

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.

32 0

Paper Graph

CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation

Minlie Huang, Chujie Zheng, Wei Chen, Yong Liu, Yongcai Leng•Mon May 17 2021

A multi-factor hierarchical framework, CoMAE, is proposed, which models the above three key factors of empathy expression in a hierarchical way and can generate more empathetic responses than previous methods.

78 0

Paper Graph

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

Devamanyu Hazarika, Soujanya Poria, Navonil Majumder, A. Gelbukh, Deepanway Ghosal, Rada Mihalcea•Mon Jun 21 2021

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.

26 0

Paper Graph

Affective Decoding for Empathetic Response Generation

Guanyi Chen, Zhigang Chen, Chenghua Lin, Chengkun Zheng, Ruizhe Li•Tue Aug 17 2021

A simple technique called Affective Decoding for empathetic response generation that can effectively incorporate emotion signals during each decoding step, and can additionally be augmented with an auxiliary dual emotion encoder, which learns separate embeddings for the speaker and listener given the emotion base of the dialogue.

9 0

Paper Graph

CEM: Commonsense-aware Empathetic Response Generation

Minlie Huang, Chujie Zheng, Sahand Sabour•Sun Sep 12 2021

This work proposes a novel approach for empathetic response generation, which leverages commonsense to draw more information about the user’s situation and uses this additional information to further enhance the empathy expression in generated responses.

181 0

Paper Graph

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

Hyunwoo Kim, Byeongchang Kim, Gunhee Kim•Fri Sep 17 2021

Taking inspiration from social cognition, a generative estimator is used to infer emotion cause words from utterances with no word-level label and a novel method based on pragmatics is introduced to make dialogue models focus on targeted words in the input during generation.

81 0

Paper Graph

Empathetic Response Generation with State Management

Ruifeng Xu, Jiachen Du, Yuhan Liu, Jun Gao, Lanjun Zhou•Fri Dec 31 2021

A novel empathetic response generation model that can consider multiple state information including emotions and intents simultaneously is proposed and dynamically managing different information can help the model generate more emPathetic responses compared with several baselines under both automatic and human evaluations.

2 0

Paper Graph

Adding a benchmark result helps the community track progress.