A Supervised Method for Extractive Single Document Summarization based on Sentence Embeddings and Neural Networks

Abstract : Extractive summarization consists of generating a summary by ranking sentences from the original texts according to their importance and salience. Text representation is a fundamental process that affects the effectiveness of many text summarization methods. Distributed word vector representations have been shown to improve Natural Language Processing (NLP) tasks, especially Automatic Text Summariza-tion (ATS). However, most of them do not consider the order and the context of the words in a sentence. This does not fully allow grasping the sentence semantics and the syntactic relationships between sentences constituents. In this paper, to overcome this problem, we propose a deep neural network model based-method for extractive single document sum-marization using the state-of-the-art sentence embedding models. Experiments are performed on the standard DUC2002 dataset using three sentence embedding models. The obtained results show the effectiveness of the used sentence embedding models for ATS. The overall comparison results show that our method outperforms eight well-known ATS baselines and achieves comparable results to the state-of-the-art deep learning based methods.
Complete list of metadatas

Cited literature [34 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02433565
Contributor : Bernard Espinasse <>
Submitted on : Thursday, January 9, 2020 - 11:25:47 AM
Last modification on : Friday, January 17, 2020 - 1:36:53 AM

File

AI2SD_2019_Lamsiyah_Salima-fin...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02433565, version 1

Collections

Citation

Salima Lamsiyah, Abdelkader El Mahdaouy, Said El Alaoui Ouatik, Bernard Espinasse. A Supervised Method for Extractive Single Document Summarization based on Sentence Embeddings and Neural Networks. AI2SD'2019 - International Conference on Advanced Intelligent Systems, Jul 2019, Marrakech, Morocco. ⟨hal-02433565⟩

Share

Metrics

Record views

33

Files downloads

52