Corpus-Based Approaches to Igbo Diacritic Restoration

With natural language processing (NLP), researchers aim to get the computer to identify and understand the patterns in human languages. This is often difficult because a language embeds many dynamic and varied properties in its syntaxes, pragmatics and phonology, which needs to be captured and processed. The capacity of computers to process natural languages is increasing because NLP researchers are pushing its boundaries. But these research works focus more on well resourced languages such as English, Japanese, German, French, Russian, Mandarin Chinese etc. Over 95% of the world’s 7000 languages are low-resourced for NLP i.e. they have little or no data, tools, and techniques for NLP work. In this thesis, we present an overview of diacritic ambiguity and a review of previous diacritic disambiguation approaches on other languages. Focusing on Igbo language, we report the steps taken to develop a flexible framework for generating datasets for diacritic restoration. Three main approaches, the standard n-gram model, the classification models and the embedding models were proposed. The standard n-gram models use a sequence of previous words to the target stripped word as key predictors of the correct variants. For the classification models, a window of words on both sides of the target stripped word were use. The embedding models compare the similarity scores of the combined context word embeddings and the embeddings of each of the candidate variant vectors. The processes and techniques involved in projecting embeddings from a model trained with English texts to an Igbo embedding space and the creation of intrinsic evaluation tasks to validate the models were also discussed. A comparative analysis of the results indicate that all the approaches significantly improved on the baseline performance which uses the unigram model. The details of the processed involved in building the models as well as the possible directions for future work are discussed in this work.