Part-of-Speech Tag Disambiguation by Cross-Linguistic Majority Vote

Abstract

In this paper, we present an approach to developing resources for a low-resource language, taking advantage of the fact that it is closely related to languages with more resources. In particular, we test our approach on Macedonian, which lacks tools for natural language processing as well as data in order to build such tools. We improve the Macedonian training set for supervised part-ofspeech tagging by transferring available manual annotations from a number of similar languages. Our approach is based on multilingual parallel corpora, automatic word alignment, and a set of rules (majority vote). The performance of a tagger trained on the improved data set of 88% accuracy is significantly better than the baseline of 76%. It can serve as a stepping stone for further improvement of resources for Macedonian. The proposed approach is entirely automatic and it can be easily adapted to other language in similar circumstances.

Learning syntactic tagging of Macedonian language

“…/ Suppose that we choose to wear ourselves out faster." confirm the assumption by Aepli et al [36] that the word classes usually match in translation. Additionally, in most of these cases, POS tag can be easily determined by the nearest previous or following word: брзо потреперување\N, брзо помина\V, брзо беше\V, ќе решиме\V побрзо.…”

“…Recently, another independent attempt to automatically POS tag the same corpus was done [36]. Tagging was based on the POS tagged versions of Bulgarian, Czech, Slovene, English and Serbian language, which were pair-aligned to Macedonian translation.…”

Multi-source morphosyntactic tagging for spoken Rusyn

“…Follow-up work has focused on the inclusion of several source languages (Fossum and Abney, 2005), more accurate projection algorithms (Das and Petrov, 2011;Duong et al, 2013), the integration of external lexicon sources (Li et al, 2012;Täckström et al, 2013), the extension from part-of-speech tagging to full morphological tagging (Buys and Botha, 2016), and the investigation of truly low-resource settings by resorting to Bible translations (Agić et al, 2015). A related approach (Aepli et al, 2014) uses majority voting to disambiguate tags proposed by several source languages. However, these projection approaches are not adapted to our setting as no parallel corpora -not even the Bible 2 -are electronically available for Rusyn.…”

“…There are essentially two ways of combining taggers: using the five source language taggers and choosing the majority vote, or using a single tagger trained on merged data from the five source corpora. Aepli et al (2014) develop a tagger for Macedonian by transferring morphosyntactic annotations from multiple source languages by word alignment, choosing one annotation by majority vote, and training a new tagger on the annotated corpus. We follow a similar method.…”

The Uniparental Genetic Landscape of Modern Slavic Speaking Populations

“…The Bulgarian literary language differs from other Slavic languages by the almost complete loss of grammatical case; the creation of definite article of nouns (appearing in the form of a suffix, added to the stem); analytical comparative and superlative (by word-particles); and a complex tense system where the infinitive is completely lost (Aepli, von Waldenfels, & Samardzic, 2014;Kushniarevich et al, 2015;Raykov, 2005).…”