Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations

Guangxiang Zhao, Jingjing Xu, Qi Zeng, Xuancheng Ren, Xu Sun


Abstract
This paper explores a new natural languageprocessing task, review-driven multi-label musicstyle classification. This task requires systemsto identify multiple styles of music basedon its reviews on websites. The biggest challengelies in the complicated relations of musicstyles. To tackle this problem, we proposea novel deep learning approach to automaticallylearn and exploit style correlations. Experiment results show that our approachachieves large improvements over baselines onthe proposed dataset. Furthermore, the visualizedanalysis shows that our approach performswell in capturing style correlations.
Anthology ID:
N19-1296
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2884–2891
Language:
URL:
https://aclanthology.org/N19-1296
DOI:
10.18653/v1/N19-1296
Bibkey:
Cite (ACL):
Guangxiang Zhao, Jingjing Xu, Qi Zeng, Xuancheng Ren, and Xu Sun. 2019. Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2884–2891, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations (Zhao et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1296.pdf
Code
 lancopku/RMSC