ПРИМЕНЕНИЕ МОРФОЛОГИЧЕСКОГО АНАЛИЗА ДЛЯ ОБОСНОВАНИЯ УПРАВЛЕНЧЕСКИХ РЕШЕНИЙ В ЛОГИСТИКЕ
This article provides a brief overview of Daba software package created in the course of building corpora for Manding languages. Key software features are motivated by the tasks and problems characteristic of many African languages. The corpus-building model proposed here was initially developed for Bambara Reference Corpus which is available online and is freely accessible. The morphological analysis procedure and corpus annotation scheme are discussed in detail. Daba uses a morpheme-based morphological annotation scheme inspired by the interlinear glossed form of presentation of linguistic examples. A scheme mapping Daba’s morpheme-based morphological information onto traditional word-based corpus annotation is provided. Since Bambara is characterized by a low level of written language standardization special attention is paid to the issues of representing variability in corpus annotation.
The problem of morphological ambiguity is widely addressed in the modern NLP. Mostly ambiguity is resolved with the use of large manually-annotated corpora and machine learning. However, such methods are not always available, as good training data is not accessible for all languages. In this paper we present a method of disambiguation without gold standard corpora using several statistical models, namely, Brill algorithm (Brill 1995) and unambiguous n-grams from the automatically annotated corpus. All the methods were tested on the Corpus of Modern Greek and on the Corpus of Modern Yiddish. As a result, more than a half of words with ambiguous analyses were disambiguated in both corpora, demonstrating high precision (>80%). Our method of morphological disambiguation demonstrates that it is possible to eliminate some of the ambiguous analyses in the corpus without specific linguistic resources, only with the use of raw data, where all possible morphological analyses for every word are indicated.