Information Extraction for Czech Based on Syntactic Analysis

Publikace nespadá pod Filozofickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu



Druh Článek ve sborníku
Konference Human Language Technology Challenges for Computer Science and Linguistics
Fakulta / Pracoviště MU

Fakulta informatiky

Obor Informatika
Klíčová slova information extraction; Czech language; syntactic analysis
Popis We present a complex pipeline of natural language processing tools for Czech that performs extraction of basic facts presented in a text. The input for the tool is a plain text, the output contains verb and noun phrases with basic semantic classification. Automatic syntactic analysis of Czech plays a crucial role in the pipeline. In this paper, we describe the particular tools used in the system, then we give an example of its usage and conclude with a basic evaluation of the overall system accuracy.
Související projekty: