The Linguistic Basis of a Rule-Based Tagger of Czech

Oliva, Karel; Hnátková, Milena; Petkevič, Vladimír; Kvėtoň, Pavel

doi:10.1007/3-540-45323-7_1

Cited by 7 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case the sentence is disambiguated fully and every word has assigned its correct tag in the given context. The recall of our system is 99.03% and the precision of 66.10% which are slightly better results in comparison with at present best Czech rule-based disambiguator [5]. Considerably better precision of disambiguation can be achieved by combining our system with efficient statistical component which is unfortunately not readily available for us now.…”

Section: Partial Automatic Disambiguationmentioning

confidence: 78%

See 1 more Smart Citation

From Czech Morphology through Partial Parsing to Disambiguation

Mráková

Sedláček

2003

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

This paper deals with a complex system of processing raw Czech texts. Several modules were implemented which perform different levels of processing. These modules can easily be incorporated into many other linguistic applications and some of them are already exploited in this way. The first level of processing raw texts represents a reliable morphological analysis -we give a survey of the effective implementation of the robust morphological analyser for Czech named ajka. Texts tagged by ajka can be further processed by the partial parser Dis and its extension VaDis which is based on verb valencies. The output of these systems serves for automatic partial disambiguation of input texts. The tools described in this paper are widely used for parsing large corpora and can be employed in the initial phase of semantic analysis.

show abstract

Section: Partial Automatic Disambiguationmentioning

confidence: 78%

“…1600 tags in ajka to 160 tags in the BNC extended tagset). Thus, it turns out that rule-based methods [5] have to be developed and employed to obtain better results.…”

Section: Introductionmentioning

confidence: 99%