The Use of ART2 to create summaries from texts of different areas
The volume of documents available electronically is growing fast, so it becomes difficult to access and select desired information in a fast and efficient way. In this context the automatic summarization task assumes a very imperative role; therefore one seeks to reduce the size of a document, pres...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Objeto de conferencia |
| Lenguaje: | Inglés |
| Publicado: |
2004
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/22561 |
| Aporte de: |
| Sumario: | The volume of documents available electronically is growing fast, so it becomes difficult to access and select desired information in a fast and efficient way.
In this context the automatic summarization task assumes a very imperative role; therefore one seeks to reduce the size of a document, preserving to the maximum its informative content. In this paper, it’s applied a model which uses sentence clusters from an ART2 neural network to generate extractive summaries. Different models can be developed from distinct area documents. Hence, the aim of this work is to evaluate the performance of those models when they summarize documents from correlated or non correlated areas. |
|---|