Presented at: The Sixth International Language Resources and Evaluation Conference (LREC2008)
by Shisanu Tongchim, Randolf Altmeyer, Virach Sornlertlamvanich, Hitoshi Isahara
Webpage: http://www.lrec-conf.org/proceedings/lrec2008/pdf/46_paper.pdfWebpage: http://www.lrec-conf.org/proceedings/lrec2008/summaries/46.html
This paper presents some preliminary results of our dependency parser for Thai. It is part of an ongoing project in developing a syntactically annotated Thai corpus. The parser has been trained and tested by using the complete part of the corpus. The parser achieves 83.64% as the root accuracy, 78.54% as the dependency accuracy and 53.90% as the complete sentence accuracy. The trained parser will be used as a preprocessing step in our corpus annotation workflow in order to accelerate the corpus development.
Keywords: Acquisition, Machine Learning, Parsing Systems, Statistical methods, Linguistics
Resource URI on the dog food server: http://data.semanticweb.org/conference/lrec/2008/papers/46
Explore this resource elsewhere: