mlsanityData to 14 Oct 2026

Using Knowledge-Embedded Attention to Augment Pre-trained Language Models for Fine-Grained Emotion Recognition

arXiv 2108.00194 ↗First posted 31 Jul 2021cs.CL cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Modern emotion recognition systems are trained to recognize only a small set of emotions, and hence fail to capture the broad spectrum of emotions people experience and express in daily life. In order to engage in more empathetic interactions, future AI has to perform textitfine-grained emotion recognition, distinguishing between many more varied emotions. Here, we focus on improving fine-grained emotion recognition by introducing external knowledge into a pre-trained self-attention model. We propose Knowledge-Embedded Attention (KEA) to use knowledge from emotion lexicons to augment the contextual representations from pre-trained ELECTRA and BERT models. Our results and error analyses outperform previous models on several datasets, and is better able to differentiate closely-confusable emotions, such as afraid and terrified.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 28 of its 49 references that are in the map. First posted on arXiv 31 Jul 2021.

Builds on

28 of 49 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  5. 2019ERNIE: Enhanced Language Representation with Informative Entitiescited by 528
  6. 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 486
  7. 2020K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapterscited by 319
  8. 2017A Structured Self-attentive Sentence Embeddingcited by 318
  9. 2019Challenges in Building Intelligent Open-domain Dialog Systemscited by 147
  10. 2019Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advancescited by 119
  11. 2020KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoningcited by 106
  12. 2019E-BERT: Efficient-Yet-Effective Entity Embeddings for BERTcited by 96
16 more
  1. 2019Knowledge-Enriched Transformer for Emotion Detection in Textual Conversationscited by 92
  2. 2019SenseBERT: Driving Some Sense into BERTcited by 73
  3. 2020SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysiscited by 54
  4. 2017Word Affect Intensitiescited by 51
  5. 2019Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Networkcited by 38
  6. 2018NTUA-SLP at SemEval-2018 Task 1: Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learningcited by 23
  7. 2019Enriching BERT with Knowledge Graph Embeddings for Document Classificationcited by 22
  8. 2019Modeling emotion in complex stories: the Stanford Emotional Narratives Datasetcited by 20
  9. 2020Context-Guided BERT for Targeted Aspect-Based Sentiment Analysiscited by 18
  10. 2020From Standard Summarization to New Tasks and Beyond: Summarization with Manifold Informationcited by 16
  11. 2019EmotionX-IDEA: Emotion BERT -- an Affectional Model for Conversationcited by 13
  12. 2016Lexicon Integrated CNN Models with Attention for Sentiment Analysiscited by 8
  13. 2019Attention-based Conditioning Methods for External Knowledge Integrationcited by 8
  14. 2019Attending to Emotional Narrativescited by 5
  15. 2021An Ethical Framework for Guiding the Development of Affectively-Aware Artificial Intelligencecited by 4
  16. 2019Joint Emotion Label Space Modelling for Affect Lexicacited by 1

Built on by

Cited by year (2026 to 14 Oct)

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

10 papers.

  1. 2021Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classificationcited by 43
  2. 2024Large Language Models Produce Responses Perceived to be Empathiccited by 36
  3. 2024Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?cited by 22
  4. 2021Natural Language Processing with Commonsense Knowledge: A Surveycited by 4
  5. 2023Using Positive Matching Contrastive Loss with Facial Action Units to mitigate bias in Facial Expression Recognitioncited by 4
  6. 2022Representing Affect Information in Word Embeddingscited by 3
  7. 2023Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learningcited by 2
  8. 2025Lotus at SemEval-2025 Task 11: RoBERTa with Llama-3 Generated Explanations for Multi-Label Emotion Classificationcited by 1
  9. 2022TamilEmo: Finegrained Emotion Detection Dataset for Tamilcited by 0
  10. 2026A Comparative Study on Affective Cues in Text Embeddings Across Psychological Emotion Theoriescited by 0