mlsanityData to 14 Oct 2026

Multi-Granularity Prompts for Topic Shift Detection in Dialogue

arXiv 2305.14006 ↗First posted 23 May 2023cs.CLcited by 6

Not on the map. Why?

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.

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

20 of 25 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  5. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  6. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  7. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 138
  8. 2020Text Segmentation by Cross Segment Attentioncited by 54
  9. 2018Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systemscited by 53
  10. 2019SECTOR: A Neural Model for Coherent Topic Segmentation and Classificationcited by 48
  11. 2020Topic-Aware Multi-turn Dialogue Modelingcited by 46
  12. 2019Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systemscited by 42
8 more
  1. 2021NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversationcited by 35
  2. 2021Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoringcited by 29
  3. 2018Attention-based Neural Text Segmentationcited by 26
  4. 2021TIAGE: A Benchmark for Topic-Shift Aware Dialog Modelingcited by 22
  5. 2021DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehensioncited by 16
  6. 2019Improving Robustness of Task Oriented Dialog Systemscited by 15
  7. 2021Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehensioncited by 13
  8. 2023Topic Shift Detection in Chinese Dialogues: Corpus and Benchmarkcited by 4

Built on by

Cited by year (2026 to 14 Oct)

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

6 papers.

  1. 2024PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapterscited by 8
  2. 2023Multi-turn Dialogue Comprehension from a Topic-aware Perspectivecited by 4
  3. 2024MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphscited by 4
  4. 2025Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-Attentioncited by 2
  5. 2026Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMscited by 0
  6. 2026CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentationcited by 0