# Toward General Semantic Chunking: A Discriminative Framework for Ultra-Long Documents

arXiv: https://arxiv.org/abs/2602.23370 · HTML: https://mlsanity.com/paper/2602.23370/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Text Segmentation as a Supervised Learning Task](https://mlsanity.com/paper/1803.09337/) (2018)
- [Extractive Summarization of Long Documents by Combining Global and Local Context](https://mlsanity.com/paper/1909.08089/) (2019)
- [Text Segmentation by Cross Segment Attention](https://mlsanity.com/paper/2004.14535/) (2020)
- [SECTOR: A Neural Model for Coherent Topic Segmentation and Classification](https://mlsanity.com/paper/1902.04793/) (2019)
- [Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation](https://mlsanity.com/paper/2001.00891/) (2020)
- [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)
- [Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence](https://mlsanity.com/paper/2110.07160/) (2021)
- [Improving Context Modeling in Neural Topic Segmentation](https://mlsanity.com/paper/2010.03138/) (2020)
- [Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling](https://mlsanity.com/paper/2310.11772/) (2023)

## Abstract (arXiv)

Long-document topic segmentation plays an important role in information retrieval and document understanding, yet existing methods still show clear shortcomings in ultra-long text settings. Traditional discriminative models are constrained by fixed windows and cannot model document-level semantics; generative large language models can output paragraph boundaries, but inference is expensive and long inputs are difficult to support. To address these issues, we propose a discriminative segmentation model based on Qwen3-0.6B. On top of the backbone network, we add a cross-window context fusion layer and a boundary classification head, and combine them with an overlapping sliding-window strategy. Our model supports single-pass inputs of up to 13k tokens and can be extended to ultra-long documents for paragraph boundary detection. To further enhance downstream retrieval efficiency, we derive a vector fusion method with scalar correction, which compresses the representation of ultra-long segments into a single vector without semantic loss. Experiments on the Wikipedia long-document topic segmentation dataset WIKI-727K show that, compared with three generative models based on Qwen2-0.5B released by Jina, our method achieves a better macro-averaged F1 and delivers two orders of magnitude faster inference, substantially improving the practicality and scalability of long-document processing.