engleski

Sentence Classification and Clause Detection for Croatian

We present a method for classifying Croatian sentences by structure and detecting independent and dependent clauses within these sentences and provide its evaluation. A prototype system applying the method was implemented by using the NooJ linguistic development environment, both for purposes of this experiment and for further utilization in a prototype rule-based chunking and shallow parsing system for Croatian. With regards to pre-processing, we implemented and evaluated three different approaches to designing the system: (1) no pre-processing of input sentences, (2) automatic morphosyntactic tagging of sentences by using the CroTag stochastic tagger and (3) manual morphosyntactic annotation of input sentences. All three approaches were evaluated for sentence classification and clause detection accuracy in terms of precision and recall. The highest scoring system was the one using sentences with manually assigned morphosyntactic tags as input and it scored an overall F1-measure of 0.861 (P: 0.928, R: 0.813). In the paper, a more detailed discussion of system design and experiment setup is provided, followed by a discussion of the obtained results and future research directions.

sentence detection; sentence classification; clause detection; Croatian language

nije evidentirano