Single document summarization using word and sentence embeddings

DOI

10.2991/jimet-15.2015.98How to use a DOI?

Keywords

Single-Document Summarization; Word Embeddings; Sentence Embeddings

Abstract

Automatic document summarization has become increasingly important in the age of big data. However, traditional summarization systems have two major weaknesses: term-vector data sparsity and semantic information deficiency. In this paper, we solve these problems by adopting word and sentence embeddings, whose distributed nature enables the relation establishment between words and sentences. Experimental result shows that our models outperform two state-of-the-art graph based summarization systems.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ayana
PY  - 2015/12
DA  - 2015/12
TI  - Single document summarization using word and sentence embeddings
BT  - Proceedings of the 2015 Joint International Mechanical, Electronic and Information Technology Conference
PB  - Atlantis Press
SP  - 523
EP  - 526
SN  - 2352-538X
UR  - https://doi.org/10.2991/jimet-15.2015.98
DO  - 10.2991/jimet-15.2015.98
ID  - 2015/12
ER  -