mlsanityData to 7 Oct 2026

Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation

arXiv 2105.11696 ↗First posted 25 May 2021cs.CLcited by 15

Not on the map. Why?

Abstract (arXiv)

For a computer to naturally interact with a human, it needs to be human-like. In this paper, we propose a neural response generation model with multi-task learning of generation and classification, focusing on emotion. Our model based on BART (Lewis et al., 2020), a pre-trained transformer encoder-decoder model, is trained to generate responses and recognize emotions simultaneously. Furthermore, we weight the losses for the tasks to control the update of parameters. Automatic evaluations and crowdsourced manual evaluations show that the proposed model makes generated responses more emotionally aware.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 15 of its 23 references that are in the map. First posted on arXiv 25 May 2021.

Builds on

15 of 23 references.

References · 15

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  5. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  6. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  7. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  8. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  9. 2019Multi-Task Deep Neural Networks for Natural Language Understandingcited by 349
  10. 2019Revealing the Dark Secrets of BERTcited by 300
  11. 2017Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memorycited by 167
  12. 2020CARE: Commonsense-Aware Emotional Response Generation with Latent Conceptscited by 20
3 more
  1. 2020EmpTransfo: A Multi-head Transformer Architecture for Creating Empathetic Dialog Systemscited by 19
  2. 2020Target Guided Emotion Aware Chat Machinecited by 10
  3. 2019Emotion helps Sentiment: A Multi-task Model for Sentiment and Emotion Analysiscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 2; 2024: 5; 2025: 1; 2026: 1.

15 papers.

Sort:

  1. 2021Contrast and Generation Make BART a Good Dialogue Emotion Recognizercited by 35
  2. 2022Recent Advances in Neural Text Generation: A Task-Agnostic Surveycited by 14
  3. 2021Generating Personalized Dialogue via Multi-Task Meta-Learningcited by 8
  4. 2022CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotionscited by 6
  5. 2024DiagESC: Dialogue Synthesis for Integrating Depression Diagnosis into Emotional Support Conversationcited by 6
  6. 2023E-CORE: Emotion Correlation Enhanced Empathetic Dialogue Generationcited by 4
  7. 2022Dynamically Retrieving Knowledge via Query Generation for Informative Dialogue Generationcited by 2
  8. 2024M3TCM: Multi-modal Multi-task Context Model for Utterance Classification in Motivational Interviewscited by 2
  9. 2024MASIVE: Open-Ended Affective State Identification in English and Spanishcited by 1
  10. 2025Advancing Multi-Party Dialogue Framework with Speaker-ware Contrastive Learningcited by 1
  11. 2026Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learningcited by 1
  12. 2022Causal Inference for Chatting Handoffcited by 0
3 more
  1. 2023Gated Mechanism Enhanced Multi-Task Learning for Dialog Routingcited by 0
  2. 2024UniRQR: A Unified Model for Retrieval Decision, Query, and Response Generation in Internet-Based Knowledge Dialogue Systemscited by 0
  3. 2024Multi-aspect Depression Severity Assessment via Inductive Dialogue Systemcited by 0