Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.23671 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910901371666432 |
|---|---|
| author | Ni, Tongke Fan, Yang Zhou, Junru Wu, Xiangping Chen, Qingcai |
| author_facet | Ni, Tongke Fan, Yang Zhou, Junru Wu, Xiangping Chen, Qingcai |
| contents | Text semantic segmentation involves partitioning a document into multiple paragraphs with continuous semantics based on the subject matter, contextual information, and document structure. Traditional approaches have typically relied on preprocessing documents into segments to address input length constraints, resulting in the loss of critical semantic information across segments. To address this, we present CrossFormer, a transformer-based model featuring a novel cross-segment fusion module that dynamically models latent semantic dependencies across document segments, substantially elevating segmentation accuracy. Additionally, CrossFormer can replace rule-based chunk methods within the Retrieval-Augmented Generation (RAG) system, producing more semantically coherent chunks that enhance its efficacy. Comprehensive evaluations confirm CrossFormer's state-of-the-art performance on public text semantic segmentation datasets, alongside considerable gains on RAG benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23671 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CrossFormer: Cross-Segment Semantic Fusion for Document Segmentation Ni, Tongke Fan, Yang Zhou, Junru Wu, Xiangping Chen, Qingcai Computation and Language Text semantic segmentation involves partitioning a document into multiple paragraphs with continuous semantics based on the subject matter, contextual information, and document structure. Traditional approaches have typically relied on preprocessing documents into segments to address input length constraints, resulting in the loss of critical semantic information across segments. To address this, we present CrossFormer, a transformer-based model featuring a novel cross-segment fusion module that dynamically models latent semantic dependencies across document segments, substantially elevating segmentation accuracy. Additionally, CrossFormer can replace rule-based chunk methods within the Retrieval-Augmented Generation (RAG) system, producing more semantically coherent chunks that enhance its efficacy. Comprehensive evaluations confirm CrossFormer's state-of-the-art performance on public text semantic segmentation datasets, alongside considerable gains on RAG benchmarks. |
| title | CrossFormer: Cross-Segment Semantic Fusion for Document Segmentation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.23671 |