Extractive summarization using siamese hierarchical transformer encoders
[EN] In this paper, we present an extractive approach to document summarization, the Siamese Hierarchical Transformer Encoders system, that is based on the use of siamese neural networks and the transformer encoders which are extended in a hierarchical way. The system, trained for binary classificat...
| Autores: | , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2020 |
| País: | España |
| Institución: | Universitat Politècnica de València (UPV) |
| Repositorio: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia |
| Idioma: | inglés |
| OAI Identifier: | oai:riunet.upv.es:10251/170290 |
| Acceso en línea: | https://riunet.upv.es/handle/10251/170290 |
| Access Level: | acceso abierto |
| Palabra clave: | Siamese neural networks Self attention Extractive summarization LENGUAJES Y SISTEMAS INFORMATICOS |
| Sumario: | [EN] In this paper, we present an extractive approach to document summarization, the Siamese Hierarchical Transformer Encoders system, that is based on the use of siamese neural networks and the transformer encoders which are extended in a hierarchical way. The system, trained for binary classification, is able to assign attention scores to each sentence in the document. These scores are used to select the most relevant sentences to build the summary. The main novelty of our proposal is the use of self-attention mechanisms at sentence level for document summarization, instead of using only attentions at word level. The experimentation carried out using the CNN/DailyMail summarization corpus shows promising results in-line with the state-of-the-art. |
|---|