Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2605.17714 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914576031809536 |
|---|---|
| author | Yoon, Hoonsang Kim, Takyoung Lee, Wonkee Cho, Ilmin Hakkani-Tür, Dilek Choi, Stanley Jungkyu |
| author_facet | Yoon, Hoonsang Kim, Takyoung Lee, Wonkee Cho, Ilmin Hakkani-Tür, Dilek Choi, Stanley Jungkyu |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17714 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Documents to Segments: A Contextual Reformulation for Topic Assignment Yoon, Hoonsang Kim, Takyoung Lee, Wonkee Cho, Ilmin Hakkani-Tür, Dilek Choi, Stanley Jungkyu Computation and Language 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 |
| title | From Documents to Segments: A Contextual Reformulation for Topic Assignment |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.17714 |