Descripción
|
|
---|---|
The paper presents a large-coverage rule-based dependency parser for Russian, ETAP-3, and results of its evaluation according to several criteria. An important feature of the parser is its ability to produce multiple parses for the same sentence. In a special mode of operation, the parser may be instructed to produce more parsing outputs in addition to the first one. Several types of data collected either empirically or from a syntactically tagged corpus of Russian, SynTagRus, are used at the filtering stage to refine the parser performance. In the evaluation, SynTagRus is viewed as a gold standard. Evaluation results show the figures of 0.900 for unlabelled attachment score, 0.860 for labeled attachment score, and 0.492 for unlabeled structure correctness | |
Internacional
|
Si |
DOI
|
|
Edición del Libro
|
|
Editorial del Libro
|
Kim Gerdes, Eva Hajicova, Leo Wanner (eds). |
ISBN
|
978-84-615-1834-0 |
Serie
|
|
Título del Libro
|
Exploring dependency grammar, semantics, and the lexicon. |
Desde página
|
318 |
Hasta página
|
327 |