SIIA Público

Título del libro: Kdir: Proceedings Of The 8th International Joint Conference On Knowledge Discovery, Knowledge Engineering And Knowledge Management - Vol. 1
Título del capítulo: Automatic Text Summarization by Non-topic Relevance Estimation

Autores UNAM:
JUAN MANUEL TORRES MORENO; GERARDO SIERRA DIAZ;

Autores externos:

Idioma:
Inglés

Año de publicación:
2016

Palabras clave:

Automatic Text Summarization; Machine Learning; Generalization Ability; Regression Estimation

Resumen:

We investigate a novel framework for Automatic Text Summarization. In this framework underlying languageuse features are learned from a minimal sample corpus. We argue the low complexity of this kind of features allows relying in generalization ability of a learning machine, rather than in diverse human-abstracted summaries. In this way, our method reliably estimates a relevance measure for predicting summary candidature scores, regardless topics in unseen documents. Our output summaries are comparable to the state-of-the-art. Thus we show that in order to extract meaning summaries, it is not crucial what is being said; but rather how it is being said.

Entidades citadas de la UNAM:

Título del libro: Kdir: Proceedings Of The 8th International Joint Conference On Knowledge Discovery, Knowledge Engineering And Knowledge Management - Vol. 1Título del capítulo: Automatic Text Summarization by Non-topic Relevance Estimation

Título del libro: Kdir: Proceedings Of The 8th International Joint Conference On Knowledge Discovery, Knowledge Engineering And Knowledge Management - Vol. 1
Título del capítulo: Automatic Text Summarization by Non-topic Relevance Estimation