# Multi-Granularity Prompts for Topic Shift Detection in Dialogue

arXiv: https://arxiv.org/abs/2305.14006 · HTML: https://mlsanity.com/paper/2305.14006/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Key-Value Retrieval Networks for Task-Oriented Dialogue](https://mlsanity.com/paper/1705.05414/) (2017)
- [Text Segmentation by Cross Segment Attention](https://mlsanity.com/paper/2004.14535/) (2020)
- [Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1804.06512/) (2018)
- [SECTOR: A Neural Model for Coherent Topic Segmentation and Classification](https://mlsanity.com/paper/1902.04793/) (2019)
- [Topic-Aware Multi-turn Dialogue Modeling](https://mlsanity.com/paper/2009.12539/) (2020)
- [Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems](https://mlsanity.com/paper/1906.09308/) (2019)
- [NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation](https://mlsanity.com/paper/2103.02548/) (2021)
- [Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring](https://mlsanity.com/paper/2106.06719/) (2021)
- [Attention-based Neural Text Segmentation](https://mlsanity.com/paper/1808.09935/) (2018)
- [TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling](https://mlsanity.com/paper/2109.04562/) (2021)
- [DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehension](https://mlsanity.com/paper/2104.12377/) (2021)
- [Improving Robustness of Task Oriented Dialog Systems](https://mlsanity.com/paper/1911.05153/) (2019)
- [Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehension](https://mlsanity.com/paper/2109.03772/) (2021)
- [Topic Shift Detection in Chinese Dialogues: Corpus and Benchmark](https://mlsanity.com/paper/2305.01195/) (2023)

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

- [PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters](https://mlsanity.com/paper/2410.16148/) (2024)
- [Multi-turn Dialogue Comprehension from a Topic-aware Perspective](https://mlsanity.com/paper/2309.09666/) (2023)
- [MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs](https://mlsanity.com/paper/2403.05814/) (2024)
- [Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-Attention](https://mlsanity.com/paper/2501.06382/) (2025)
- [Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMs](https://mlsanity.com/paper/2605.09268/) (2026)
- [CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentation](https://mlsanity.com/paper/2605.30668/) (2026)

## Abstract (arXiv)

The goal of dialogue topic shift detection is to identify whether the current topic in a conversation has changed or needs to change. Previous work focused on detecting topic shifts using pre-trained models to encode the utterance, failing to delve into the various levels of topic granularity in the dialogue and understand dialogue contents. To address the above issues, we take a prompt-based approach to fully extract topic information from dialogues at multiple-granularity, i.e., label, turn, and topic. Experimental results on our annotated Chinese Natural Topic Dialogue dataset CNTD and the publicly available English TIAGE dataset show that the proposed model outperforms the baselines. Further experiments show that the information extracted at different levels of granularity effectively helps the model comprehend the conversation topics.