mlsanityData to 7 Oct 2026

Consistent Kernel Change-Point Detection under m-Dependence for Text Segmentation

arXiv 2510.03437 ↗First posted 3 Oct 2025cs.LG cs.CL stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Kernel change-point detection (KCPD) has become a widely used tool for identifying structural changes in complex data. While existing theory establishes consistency under independence assumptions, real-world sequential data such as text exhibits strong dependencies. We establish new guarantees for KCPD under m-dependent data: specifically, we prove consistency in the number of detected change points and weak consistency in their locations under mild additional assumptions. We perform an LLM-based simulation that generates synthetic m-dependent text to validate the asymptotics. To complement these results, we present the first comprehensive empirical study of KCPD for text segmentation with modern embeddings. Across diverse text datasets, KCPD with text embeddings outperforms baselines in standard text segmentation metrics. We demonstrate through a case study on Taylor Swift's tweets that KCPD not only provides strong theoretical and simulated reliability but also practical effectiveness for text segmentation tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 58 references that are in the map. First posted on arXiv 3 Oct 2025.

Builds on

20 of 58 references.

References · 20

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  4. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
  5. 2018Text Segmentation as a Supervised Learning Taskcited by 76
  6. 2020Text Segmentation by Cross Segment Attentioncited by 54
  7. 2020Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentationcited by 41
  8. 2019Kernel Change-point Detection with Auxiliary Deep Generative Modelscited by 32
  9. 2021Unsupervised Topic Segmentation of Meetings with BERT Embeddingscited by 30
  10. 2022Toward Unifying Text Segmentation and Long Document Summarizationcited by 28
  11. 2018Attention-based Neural Text Segmentationcited by 26
  12. 2020Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programmingcited by 25
8 more
  1. 2016Multiple-change-point detection for high dimensional time series via sparsified binary segmentationcited by 24
  2. 2016High-dimensional changepoint estimation via sparse projectioncited by 20
  3. 2023Improving Long Document Topic Segmentation Models With Enhanced Coherence Modelingcited by 15
  4. 2020Online Neural Networks for Change-Point Detectioncited by 8
  5. 2020Online change-point detection with kernelscited by 7
  6. 2018Structural Breaks in Time Seriescited by 5
  7. 2023Selective Inference for Changepoint detection by Recurrent Neural Networkcited by 4
  8. 2024TreeSeg: Hierarchical Topic Segmentation of Large Transcriptscited by 3

Built on by

Not cited yet.