Abstract
This paper proposes a scheme for content based keyword generation of song lyrics. Syntactic as well semantic similarity is used for sentence level clustering to separate the topic from the background of a song. A method is proposed to search for a center in the semantic graph ofWord- Net for generating keywords not contained in original text.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings of the 8th International Conference on Music Information Retrieval, ISMIR 2007 |
| Pages | 121-122 |
| Number of pages | 2 |
| State | Published - Dec 1 2007 |
| Externally published | Yes |
| Event | 8th International Conference on Music Information Retrieval, ISMIR 2007 - Vienna, Austria Duration: Sep 23 2007 → Sep 27 2007 |
Publication series
| Name | Proceedings of the 8th International Conference on Music Information Retrieval, ISMIR 2007 |
|---|
Other
| Other | 8th International Conference on Music Information Retrieval, ISMIR 2007 |
|---|---|
| Country | Austria |
| City | Vienna |
| Period | 9/23/07 → 9/27/07 |
ASJC Scopus subject areas
- Music
- Information Systems
Fingerprint Dive into the research topics of 'Keyword generation for lyrics'. Together they form a unique fingerprint.
Cite this
Wei, B., Zhang, C., & Ogihara, M. (2007). Keyword generation for lyrics. In Proceedings of the 8th International Conference on Music Information Retrieval, ISMIR 2007 (pp. 121-122). (Proceedings of the 8th International Conference on Music Information Retrieval, ISMIR 2007).