Abstract | ||
---|---|---|
In this paper, we describe an automatic Korean word spacing approach using structural SVMs to relax the independence assumptions required by HMMs. We use a Pegasos algorithm for fast training of structural SVMs. We show the Pegasos algorithm for structural SVMs outperforms significantly HMMs and traditional binary SVMs, and it is much faster than CRFs and structural SVMs without loss of performance. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1016/j.ipm.2012.05.004 | Inf. Process. Manage. |
Keywords | Field | DocType |
traditional binary svms,fast training,structural svms,automatic korean word,pegasos algorithm,independence assumption | Pattern recognition,Computer science,Support vector machine,Algorithm,Speech recognition,Artificial intelligence,CRFS,Binary number | Journal |
Volume | Issue | ISSN |
49 | 1 | 0306-4573 |
Citations | PageRank | References |
3 | 0.42 | 17 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Changki Lee | 1 | 279 | 26.18 |
Hyun-Ki Kim | 2 | 61 | 21.35 |