Abstract | ||
---|---|---|
Palmer ((4)) demonstrated how Brill's Transformation-bas ed Error-Driven Learning can be applied to word segmentation in various languages. We present exper imental results which show that such al- gorithms can achieve satisfactory performance even with a a very simple initial state annotator We also present two preliminary studies, which suggest that even hi gher performance might be achieved if simple morphological information is available to the system, and t hat segmentation performance might actually be improved by combining segmentation with rudimentary par t-of-speech tagging. |
Year | Venue | Keywords |
---|---|---|
1998 | PACLIC | word segmentation |
Field | DocType | Citations |
Scale-space segmentation,Segmentation,Computer science,Segmentation-based object categorization,Speech recognition,Text segmentation,Speech segmentation,Error-driven learning | Conference | 13 |
PageRank | References | Authors |
2.02 | 4 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Julia Hockenmaier | 1 | 1782 | 114.23 |
Chris Brew | 2 | 321 | 44.44 |