Revista: | Computación y sistemas |
Base de datos: | |
Número de sistema: | 000560462 |
ISSN: | 1405-5546 |
Autors: | Gutiérrez Hinojosa, Sandra J1 Calvo, Hiram1 Moreno Armendáriz, Marco A1 |
Institucions: | 1Instituto Politécnico Nacional, Centro de Investigación en Computación, Ciudad de México. México |
Any: | 2019 |
Període: | Jul-Sep |
Volum: | 23 |
Número: | 3 |
Paginació: | 649-663 |
País: | México |
Idioma: | Inglés |
Tipo de documento: | Artículo |
Resumen en inglés | In this work we propose using word embeddings combined with unsupervised methods such as clustering for the multi-document summarization task of DUC (Document Understanding Conference) 2002. We aim to find evidence that semantic information is kept in word embeddings and this representation is subject to be grouped based on their similarity, so that main ideas can be identified in sets of documents. We experiment with different clustering methods to extract candidates for the multi-document summarization task. Our experiments show that our method is able to find the prevalent ideas. ROUGE measures of our experiments are similar to the state of the art, despite the fact that not all the main ideas are found; as our method does not require annotated resources, it provides a domain and language independent way to create a summary. |
Disciplines | Ciencias de la computación |
Paraules clau: | Inteligencia artificial |
Keyword: | Extractive summarization, Prevalent ideas extraction, Concept similarity, Central embeddings, DUC 2002, Artificial intelligence |
Text complet: | Texto completo (Ver HTML) Texto completo (Ver PDF) |