Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Wide R. Hogenhout"'
Autor:
Yuji Matsumoto, Wide R. Hogenhout
Publikováno v:
Natural Language Engineering. 4:191-209
The statistical induction of stochastic context free grammars from bracketed corpora with the Inside Outside Algorithm is an appealing method for grammar learning, but the computational complexity of this algorithm has made it impossible to generate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4eac2c5b8d0d5f845ffde8105a003bdb
https://doi.org/10.1017/s1351324998001983
https://doi.org/10.1017/s1351324998001983
Autor:
Wide R. Hogenhout, Yuji Matsumoto
Publikováno v:
Journal of Natural Language Processing. 5:25-46
We show how a treebank can be used to cluster words on the basis of their syntactic behavior. By extracting statistics on the structures in which words appear it is possible to discover similarities and differences in usage between words with the sam
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::931f51fa04afc2b738d0878aac737991
https://doi.org/10.5715/jnlp.5.2_25
https://doi.org/10.5715/jnlp.5.2_25
Autor:
Yuji Matsumoto, Wide R. Hogenhout
Publikováno v:
Proceedings of the International Workshop on Finite State Methods in Natural Language Processing - FSMNLP '09.
Recent approaches to statistical parsing include those that estimate an approximation of a stochastic, lexicalized grammar directly from a treebank and others that rebuild trees with a number of tree-constructing operators, which are applied in order
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e2ae39512deee1530bb984bac1e43ec6
https://doi.org/10.3115/1611533.1611537
https://doi.org/10.3115/1611533.1611537
Autor:
Yuji Matsumoto, Wide R. Hogenhout
Publikováno v:
COLING
Since treebanks have become available to researchers a wide variety of techniques has been used to make broad coverage parsing systems. This makes quantitative evaluation very important, but the current evaluation methods have a number of drawbacks s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e6d5dba108e659455e7f49dedb8c6753
https://doi.org/10.3115/992628.992725
https://doi.org/10.3115/992628.992725