Bidirectional LSTM-CRF Model and POS for Article Title Summarization

DOI

10.2991/ncce-18.2018.59How to use a DOI?

Keywords

Bidirectional LSTM-CRF; title summarization; POS; word2vec.

Abstract

In this paper, we propose a method based on Bidirectional LSTM-CRF for article title summarization. And for the summary generated by the model is not compliant with the grammar rules problem, we use POS (Part of Speech) to revise the generated summary. In order to verity our method, we conducted an experiment with the article title of WeChat public number. The results show that our method is effective, and POS can make results consistent with grammar rules and read fluently

Copyright

© 2018, 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  - Xiaofeng Cai
AU  - Zhifeng Hao
PY  - 2018/05
DA  - 2018/05
TI  - Bidirectional LSTM-CRF Model and POS for Article Title Summarization
BT  - Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)
PB  - Atlantis Press
SP  - 371
EP  - 375
SN  - 1951-6851
UR  - https://doi.org/10.2991/ncce-18.2018.59
DO  - 10.2991/ncce-18.2018.59
ID  - Cai2018/05
ER  -