Сегментные правила в автоматическом парсере корпуса хакасского языка

Урало-алтайские исследования. 2019. № 1(32). С. 48–69.

Dybo A., Крылов Ф. С., Мальцева В. С., Шеймович А. В.

The article describes a fragment of the work process of an automatic parser for Literary Khakass. It analyzes data using “synthesis”, i. e., through multiPLe straight and reverse passes that check various hypotheses. The article describes the transformation of a morphophonological transcription of a word-form into an orthographic one. Literary Khakass is not very normative as a language, and existing grammars do not reflect every feature of its morphophonology well enough. Thus, for some stages of the process we use rules derived from our analysis of the corpus data and of the dialectal materials we have collected.

Keywords: language corpora, лингвистический корпус, морфонология, morphophonology, автоматический морфологический анализ, хакасский язык, Khakas language, agglutination, automatic parsing, агглютинация