mlsanityData to 7 Oct 2026

Modulating Language Models with Emotions

arXiv 2108.07886 ↗First posted 17 Aug 2021cs.CL cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Generating context-aware language that embodies diverse emotions is an important step towards building empathetic NLP systems. In this paper, we propose a formulation of modulated layer normalization -- a technique inspired by computer vision -- that allows us to use large-scale language models for emotional response generation. In automatic and human evaluation on the MojiTalk dataset, our proposed modulated layer normalization method outperforms prior baseline methods while maintaining diversity, fluency, and coherence. Our method also obtains competitive performance even when using only 10% of the available training data.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 48 of its 62 references that are in the map. First posted on arXiv 17 Aug 2021.

Builds on

48 of 62 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  7. 2016Layer Normalizationcited by 5,579
  8. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  9. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  10. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  11. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  12. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
36 more
  1. 2018Hierarchical Neural Story Generationcited by 1,182
  2. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  3. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  4. 2018Self-Attention Generative Adversarial Networkscited by 809
  5. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  6. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  7. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  8. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  9. 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 375
  10. 2016Deep Reinforcement Learning for Dialogue Generationcited by 286
  11. 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
  12. 2018cGANs with Projection Discriminatorcited by 253
  13. 2019Simple, Scalable Adaptation for Neural Machine Translationcited by 239
  14. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  15. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  16. 2020Synthesizer: Rethinking Self-Attention in Transformer Modelscited by 204
  17. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
  18. 2019Leveraging Pre-trained Checkpoints for Sequence Generation Taskscited by 182
  19. 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
  20. 2017Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memorycited by 167
  21. 2017Modulating early visual processing by languagecited by 167
  22. 2019Bridging the Gap between Training and Inference for Neural Machine Translationcited by 123
  23. 2019Generalization in Generation: A closer look at Exposure Biascited by 123
  24. 2017Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasmcited by 117
  25. 2017Adversarial Learning for Neural Dialogue Generationcited by 103
  26. 2020Dialogue Response Ranking Training with Large-Scale Human Feedback Datacited by 68
  27. 2017MojiTalk: Generating Emotional Responses at Scalecited by 64
  28. 2018DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encodercited by 44
  29. 2020CDL: Curriculum Dual Learning for Emotion-Controllable Response Generationcited by 43
  30. 2018Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learningcited by 21
  31. 2021Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interactioncited by 21
  32. 2018A Hierarchical Latent Structure for Variational Conversation Modelingcited by 17
  33. 2017A Conditional Variational Framework for Dialog Generationcited by 16
  34. 2020StyleDGPT: Stylized Response Generation with Pre-trained Language Modelscited by 10
  35. 2019Low-Resource Response Generation with Template Priorcited by 9
  36. 2019An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 1; 2024: 3; 2025: 1; 2026: 1.

9 papers.

  1. 2021Unified Named Entity Recognition as Word-Word Relation Classificationcited by 89
  2. 2024Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attributioncited by 39
  3. 2023Paralinguistics-Enhanced Large Language Modeling of Spoken Dialoguecited by 25
  4. 2022Language Detoxification with Attribute-Discriminative Latent Spacecited by 11
  5. 2022TOE: A Grid-Tagging Discontinuous NER Model Enhanced by Embedding Tag/Word Relations and More Fine-Grained Tagscited by 8
  6. 2024Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generationcited by 7
  7. 2024EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domaincited by 1
  8. 2025SEDA: A Self-Adapted Entity-Centric Data Augmentation for Boosting Gird-based Discontinuous NER Modelscited by 0
  9. 2026Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Textscited by 0