Finding the correct interpretation of Swedish compounds, a statistical approach (2004)
by
Jonas Sjöbergh
,
Viggo Kann
| Venue: | In Proc. 4th Int. Conf. Language Resources and Evaluation (LREC |
| Citations: | 7 - 0 self |
BibTeX
@INPROCEEDINGS{Sjöbergh04findingthe,
author = {Jonas Sjöbergh and Viggo Kann},
title = {Finding the correct interpretation of Swedish compounds, a statistical approach},
booktitle = {In Proc. 4th Int. Conf. Language Resources and Evaluation (LREC},
year = {2004},
pages = {899--902}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper treats compound splitting for Swedish, where compounding is productive and very common. A method for splitting compounds and several methods for choosing the correct interpretation of ambiguous compounds are presented. 99 % of all compounds are split, 97 % of these are correctly interpreted. 1.
Citations
| 293 | Tnt – a statistical part-ofspeech tagger - Brants - 1996 |
| 46 | The linguistic annotation system of the Stockholm-Umeå corpus project - Ejerhed, Källgren, et al. - 1992 |
| 45 | Empirical methods for compound splitting - Koehn, Knight - 2003 |
| 27 | The World’s Major Languages - Comrie - 1990 |
| 19 | Detection of spelling errors in Swedish not using a word list en clair - Domeij, Hollman, et al. - 1994 |
| 15 | Implementaion Aspects and Applications of a Spelling Correction Algorithm - Kann, Domeij, et al. - 1998 |
| 10 | Corpus-driven splitting of compound words - Brown - 2002 |
| 5 | Parsing words - Dura - 1998 |
| 2 | An automatic analysis of Norwegian compounds - Johannessen, Hauglin - 1996 |
| 1 | Sense-tagging at the cycle-level using GLDB - Kokkinakis, Kokkinakis - 1999 |
