# Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention

arXiv: https://arxiv.org/abs/2305.00262 · HTML: https://mlsanity.com/paper/2305.00262/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 29 Apr 2023.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [DialogueRNN: An Attentive RNN for Emotion Detection in Conversations](https://mlsanity.com/paper/1811.00405/) (2018)
- [COSMIC: COmmonSense knowledge for eMotion Identification in Conversations](https://mlsanity.com/paper/2010.02795/) (2020)
- [Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks](https://mlsanity.com/paper/1708.04299/) (2017)
- [DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition](https://mlsanity.com/paper/2012.08695/) (2020)
- [Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots](https://mlsanity.com/paper/2004.03588/) (2020)
- [Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2004.08056/) (2020)
- [Hierarchical Pre-training for Sequence Labelling in Spoken Dialog](https://mlsanity.com/paper/2009.11152/) (2020)
- [GDPNet: Refining Latent Multi-View Graph for Relation Extraction](https://mlsanity.com/paper/2012.06780/) (2020)
- [Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks](https://mlsanity.com/paper/1603.03827/) (2016)
- [Dialogue Act Classification with Context-Aware Self-Attention](https://mlsanity.com/paper/1904.02594/) (2019)
- [Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue](https://mlsanity.com/paper/2009.06504/) (2020)
- [Graph Based Network with Contextualized Representations of Turns in Dialogue](https://mlsanity.com/paper/2109.04008/) (2021)
- [Dialogue Act Recognition via CRF-Attentive Structured Network](https://mlsanity.com/paper/1711.05568/) (2017)
- [An Embarrassingly Simple Model for Dialogue Relation Extraction](https://mlsanity.com/paper/2012.13873/) (2020)

## Built on by (most cited first, 6 of 6)

- [InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2309.11911/) (2023)
- [Empirical Analysis of Dialogue Relation Extraction with Large Language Models](https://mlsanity.com/paper/2404.17802/) (2024)
- [Samsung Research China-Beijing at SemEval-2024 Task 3: A multi-stage framework for Emotion-Cause Pair Extraction in Conversations](https://mlsanity.com/paper/2404.16905/) (2024)
- [Subversive Characters and Stereotyping Readers: Characterizing Queer Relationalities with Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2410.14978/) (2024)
- [SentiXRL: An advanced large language Model Framework for Multilingual Fine-Grained Emotion Classification in Complex Text Environment](https://mlsanity.com/paper/2411.18162/) (2024)
- [A Dynamic and High-Precision Method for Scenario-Based HRA Synthetic Data Collection in Multi-Agent Collaborative Environments Driven by LLMs](https://mlsanity.com/paper/2502.00022/) (2025)

## Abstract (arXiv)

Compared with standard text, understanding dialogue is more challenging for machines as the dynamic and unexpected semantic changes in each turn. To model such inconsistent semantics, we propose a simple but effective Hierarchical Dialogue Understanding model, HiDialog. Specifically, we first insert multiple special tokens into a dialogue and propose the turn-level attention to learn turn embeddings hierarchically. Then, a heterogeneous graph module is leveraged to polish the learned embeddings. We evaluate our model on various dialogue understanding tasks including dialogue relation extraction, dialogue emotion recognition, and dialogue act classification. Results show that our simple approach achieves state-of-the-art performance on all three tasks above. All our source code is publicly available at https://github.com/ShawX825/HiDialog.