# From Documents to Segments: A Contextual Reformulation for Topic Assignment

arXiv: https://arxiv.org/abs/2605.17714 · HTML: https://mlsanity.com/paper/2605.17714/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 43 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 9 of 9)

- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Topic Modeling in Embedding Spaces](https://mlsanity.com/paper/1907.04907/) (2019)
- [Regularizing and Optimizing LSTM Language Models](https://mlsanity.com/paper/1708.02182/) (2017)
- [Autoencoding Variational Inference For Topic Models](https://mlsanity.com/paper/1703.01488/) (2017)
- [SECTOR: A Neural Model for Coherent Topic Segmentation and Classification](https://mlsanity.com/paper/1902.04793/) (2019)
- [Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study](https://mlsanity.com/paper/2305.08391/) (2023)
- [Contextualized Topic Coherence Metrics](https://mlsanity.com/paper/2305.14587/) (2023)
- [Generative AI for automatic topic labelling](https://mlsanity.com/paper/2408.07003/) (2024)
- [TopicTag: Automatic Annotation of NMF Topic Models Using Chain of Thought and Prompt Tuning with LLMs](https://mlsanity.com/paper/2407.19616/) (2024)

## Abstract (arXiv)

Traditional topic modeling assigns a single topic to each document. In practice, however, many real-world documents, such as product reviews or open-ended survey responses, contain multiple distinct topics. This mismatch often leads to topic contamination, where unrelated themes are merged into a single topic, making it difficult to identify documents that truly focus on a specific subject. We address this issue by introducing segment-based topic allocation (SBTA), a reformulation of topic modeling that assigns topics not to entire documents, but to segments: short, coherent spans of text that each express a single theme. By modeling topical structure at the segment level, our approach yields cleaner and more interpretable topics and better supports analysis of multi-theme documents. To support systematic evaluation, we construct a SemEval-STM, a new dataset inspired by aspect-based sentiment analysis. Documents are first decomposed into topical segments using large language models (LLMs), followed by human refinement to ensure segment quality. We also propose a segment-level extension of the word intrusion task, enabling human evaluation of topical coherence at the granularity where topics are actually assigned. Across multiple models and evaluation metrics, we show that SBTA improves clustering quality and interpretability. Overall, this work provides a practical, scalable framework for fine-grained topic analysis in heterogeneous text corpora where documents naturally span multiple topics. URL: https://huggingface.co/datasets/LG-AI-Research/SemEval-STM