A Rate-Distortion Framework for Summarization
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908345324011520 |
|---|---|
| author | Arda, Enes Yener, Aylin |
| author_facet | Arda, Enes Yener, Aylin |
| contents | This paper introduces an information-theoretic framework for text summarization. We define the summarizer rate-distortion function and show that it provides a fundamental lower bound on summarizer performance. We describe an iterative procedure, similar to Blahut-Arimoto algorithm, for computing this function. To handle real-world text datasets, we also propose a practical method that can calculate the summarizer rate-distortion function with limited data. Finally, we empirically confirm our theoretical results by comparing the summarizer rate-distortion function with the performances of different summarizers used in practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13100 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Rate-Distortion Framework for Summarization Arda, Enes Yener, Aylin Information Theory Computation and Language Machine Learning This paper introduces an information-theoretic framework for text summarization. We define the summarizer rate-distortion function and show that it provides a fundamental lower bound on summarizer performance. We describe an iterative procedure, similar to Blahut-Arimoto algorithm, for computing this function. To handle real-world text datasets, we also propose a practical method that can calculate the summarizer rate-distortion function with limited data. Finally, we empirically confirm our theoretical results by comparing the summarizer rate-distortion function with the performances of different summarizers used in practice. |
| title | A Rate-Distortion Framework for Summarization |
| topic | Information Theory Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2501.13100 |