Homonymy between oikonyms and anthroponyms ending in -slav/-slava as a problem of automatic morphological analysis Cover Image

Homonymie mezi oikonymy a antroponymy zakončenými na -slav/-slava jako problém automatické morfologické analýzy
Homonymy between oikonyms and anthroponyms ending in -slav/-slava as a problem of automatic morphological analysis

Author(s): Klára Osolsobě, Hana Žižková
Subject(s): Computational linguistics
Published by: AV ČR - Akademie věd České republiky - Ústav pro jazyk český
Keywords: anthroponym; oikonym; ending in -slav/-slava; corpus; tagging; disambiguation

Summary/Abstract: Homonymy at all levels, which is a distinct feature of all natural languages, is alsoone of the most significant obstacles to automatic natural language processing.In this paper, we will point out the morphosyntactic differences of Czech anthroponymsending in -slav ( Miroslav-type, masculine) and Czech oikonyms with thesame ending (Miroslav-type, feminine) and Czech anthroponyms ending in -slava(Miroslava-type feminine, because its forms are homonymous with both: masculineanthroponyms and feminine oikonyms). The analysis of data from the Syn v8 corpusshows that word form homonymy significantly influences the results of automaticmorphological analysis. We will document errors in the coverage of the automaticanalyzer dictionary and, above all, errors in morphological tagging, and we will proposea solution to partially improve the automatic disambiguation of the given typeof proper nouns.

  • Issue Year: 62/2021
  • Issue No: 2
  • Page Range: 377-403
  • Page Count: 27
  • Language: Czech