Sign Language Keyword Extraction based on GLOSS

DOI

10.2991/icmeit-19.2019.51How to use a DOI?

Keywords

Gloss; sign language; keyword extraction; Word2vec.

Abstract

In order to quickly understand the content of sign language video, the theme of handshake language, and facilitate the efficient management and retrieval of sign language corpus, the annotation corpus in the parallel corpus of the text first maps all words to one using the word2vec model based on deep learning tools. Abstract word vector space; then word clustering based on K-means algorithm to achieve keyword extraction. Experiments show that the algorithm has better keyword extraction effect for sign language videos with more keywords and longer video time.

Copyright

© 2019, 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  - Ruizhu Wu
PY  - 2019/04
DA  - 2019/04
TI  - Sign Language Keyword Extraction based on GLOSS
BT  - Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)
PB  - Atlantis Press
SP  - 296
EP  - 300
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmeit-19.2019.51
DO  - 10.2991/icmeit-19.2019.51
ID  - Wu2019/04
ER  -