A unified framework for keywords distillation and summarization

DOI

10.2991/meita-15.2015.122How to use a DOI?

Keywords

keywords distillation; document summarization; similarity method; graph based algorithm;

Abstract

Keywords distillation and document summarization are important task for many text applications. Existing methods have been conducting these two tasks separately without considering the relationship between the two tasks. In order to capture and make better use of their relationships between these tasks, this paper proposed a unified framework for keyword extraction and summarization. The method is first implemented by constructing a graph which reflect relationship between different size of granularity nodes, and then using graph based algorithm to calculate score of keywords and sentences. Finally, highest score of words and sentences in the document will be chosen as keywords and salient sentence. Experimental results show that our approach outperforms baseline methods.

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  - Wei Yang
PY  - 2015/08
DA  - 2015/08
TI  - A unified framework for keywords distillation and summarization
BT  - Proceedings of the 2015 International Conference on Materials Engineering and Information Technology Applications
PB  - Atlantis Press
SP  - 671
EP  - 676
SN  - 2352-5401
UR  - https://doi.org/10.2991/meita-15.2015.122
DO  - 10.2991/meita-15.2015.122
ID  - Yang2015/08
ER  -