# Unsupervised Text Segmentation via Kernel Change-Point Detection on Sentence Embeddings

arXiv: https://arxiv.org/abs/2601.18788 · HTML: https://mlsanity.com/paper/2601.18788/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Text Segmentation as a Supervised Learning Task](https://mlsanity.com/paper/1803.09337/) (2018)
- [Text Segmentation by Cross Segment Attention](https://mlsanity.com/paper/2004.14535/) (2020)
- [Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation](https://mlsanity.com/paper/2001.00891/) (2020)
- [Kernel Change-point Detection with Auxiliary Deep Generative Models](https://mlsanity.com/paper/1901.06077/) (2019)
- [Unsupervised Topic Segmentation of Meetings with BERT Embeddings](https://mlsanity.com/paper/2106.12978/) (2021)
- [Toward Unifying Text Segmentation and Long Document Summarization](https://mlsanity.com/paper/2210.16422/) (2022)
- [Attention-based Neural Text Segmentation](https://mlsanity.com/paper/1808.09935/) (2018)
- [Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming](https://mlsanity.com/paper/2002.09132/) (2020)
- [Multiple-change-point detection for high dimensional time series via sparsified binary segmentation](https://mlsanity.com/paper/1611.08639/) (2016)
- [High-dimensional changepoint estimation via sparse projection](https://mlsanity.com/paper/1606.06246/) (2016)
- [Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling](https://mlsanity.com/paper/2310.11772/) (2023)
- [Online Neural Networks for Change-Point Detection](https://mlsanity.com/paper/2010.01388/) (2020)
- [Online change-point detection with kernels](https://mlsanity.com/paper/2002.02704/) (2020)
- [Structural Breaks in Time Series](https://mlsanity.com/paper/1805.03807/) (2018)
- [Selective Inference for Changepoint detection by Recurrent Neural Network](https://mlsanity.com/paper/2311.14964/) (2023)
- [TreeSeg: Hierarchical Topic Segmentation of Large Transcripts](https://mlsanity.com/paper/2407.12028/) (2024)

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

- [Computational Measurement of Team-Process Phase Dynamics in Collaborative Virtual Reality](https://mlsanity.com/paper/2608.18660/) (2026)

## Abstract (arXiv)

Unsupervised text segmentation is crucial because boundary labels are expensive, subjective, and often fail to transfer across domains and granularity choices. We propose Embed-KCPD, a training-free method that represents sentences as embedding vectors and estimates boundaries by minimizing a penalized KCPD objective. Beyond the algorithmic instantiation, we develop, to our knowledge, the first dependence-aware theory for KCPD under m-dependent sequences, a finite-memory abstraction of short-range dependence common in language. We prove an oracle inequality for the population penalized risk and a localization guarantee showing that each true change point is recovered within a window that is small relative to segment length. To connect theory to practice, we introduce an LLM-based simulation framework that generates synthetic documents with controlled finite-memory dependence and known boundaries, validating the predicted scaling behavior. Across standard segmentation benchmarks, Embed-KCPD often outperforms strong unsupervised baselines. A case study on Taylor Swift's tweets illustrates that Embed-KCPD combines strong theoretical guarantees, simulated reliability, and practical effectiveness for text segmentation.