NotesFAQContact Us
Search Tips
ERIC Number: ED413757
Record Type: Non-Journal
Publication Date: 1995
Pages: 7
Abstractor: N/A
Reference Count: N/A
A Simple Czech and English Probabilistic Tagger: A Comparison.
Hladka, Barbora; Hajic, Jan
An experiment compared the tagging of two languages: Czech, a highly inflected language with a high degree of ambiguity, and English. For Czech, the corpus was one gathered in the 1970s at the Czechoslovak Academy of Sciences; for English, it was the Wall Street Journal corpus. Results indicate 81.53 percent accuracy for Czech and 96.83 percent accuracy for English, representing a higher level of accuracy than expected for Czech. Several simple improvements in the Czech tagging system were identified. (MSE)
Publication Type: Reports - Descriptive; Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A