# FATRER: Full-Attention Topic Regularizer for Accurate and Robust Conversational Emotion Recognition

arXiv: https://arxiv.org/abs/2307.12221 · HTML: https://mlsanity.com/paper/2307.12221/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 54 references that are in the map.
- First posted on arXiv 23 Jul 2023.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [DialogueRNN: An Attentive RNN for Emotion Detection in Conversations](https://mlsanity.com/paper/1811.00405/) (2018)
- [DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation](https://mlsanity.com/paper/1908.11540/) (2019)
- [Autoencoding Variational Inference For Topic Models](https://mlsanity.com/paper/1703.01488/) (2017)
- [COSMIC: COmmonSense knowledge for eMotion Identification in Conversations](https://mlsanity.com/paper/2010.02795/) (2020)
- [Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence](https://mlsanity.com/paper/2004.03974/) (2020)
- [Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advances](https://mlsanity.com/paper/1905.02947/) (2019)
- [Measure and Improve Robustness in NLP Models: A Survey](https://mlsanity.com/paper/2112.08313/) (2021)
- [Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks](https://mlsanity.com/paper/1708.04299/) (2017)
- [Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations](https://mlsanity.com/paper/1909.10681/) (2019)
- [DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition](https://mlsanity.com/paper/2012.08695/) (2020)
- [Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection](https://mlsanity.com/paper/2106.01071/) (2021)
- [Neural Topic Model via Optimal Transport](https://mlsanity.com/paper/2008.13537/) (2020)
- [Topic Modeling with Contextualized Word Representation Clusters](https://mlsanity.com/paper/2010.12626/) (2020)
- [Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network](https://mlsanity.com/paper/1911.09075/) (2019)
- [Contrast and Generation Make BART a Good Dialogue Emotion Recognizer](https://mlsanity.com/paper/2112.11202/) (2021)
- [Coherence-Aware Neural Topic Modeling](https://mlsanity.com/paper/1809.02687/) (2018)
- [Improving Neural Topic Models using Knowledge Distillation](https://mlsanity.com/paper/2010.02377/) (2020)
- [Document Informed Neural Autoregressive Topic Models with Distributional Prior](https://mlsanity.com/paper/1809.06709/) (2018)
- [Utterance-level Dialogue Understanding: An Empirical Study](https://mlsanity.com/paper/2009.13902/) (2020)
- [TAN-NTM: Topic Attention Networks for Neural Topic Modeling](https://mlsanity.com/paper/2012.01524/) (2020)
- [Conversational Transfer Learning for Emotion Recognition](https://mlsanity.com/paper/1910.04980/) (2019)
- [TDAM: a Topic-Dependent Attention Model for Sentiment Analysis](https://mlsanity.com/paper/1908.06435/) (2019)

## Built on by (most cited first, 1 of 1)

- [GatedxLSTM: A Multimodal Affective Computing Approach for Emotion Recognition in Conversations](https://mlsanity.com/paper/2503.20919/) (2025)

## Abstract (arXiv)

This paper concentrates on the understanding of interlocutors' emotions evoked in conversational utterances. Previous studies in this literature mainly focus on more accurate emotional predictions, while ignoring model robustness when the local context is corrupted by adversarial attacks. To maintain robustness while ensuring accuracy, we propose an emotion recognizer augmented by a full-attention topic regularizer, which enables an emotion-related global view when modeling the local context in a conversation. A joint topic modeling strategy is introduced to implement regularization from both representation and loss perspectives. To avoid over-regularization, we drop the constraints on prior distributions that exist in traditional topic modeling and perform probabilistic approximations based entirely on attention alignment. Experiments show that our models obtain more favorable results than state-of-the-art models, and gain convincing robustness under three types of adversarial attacks.