Towards Building Stemmer for Tenyidie Language

The Tenyidie language is a Tibeto-Burman Language of Nagaland in the north-eastern part of India. Tenyidie is a low-resource language spoken by the Tenyimia Community and is considered a major language in Nagaland. Tenyidie is a tonal, Subject-Object-Verb, and highly agglutinative language. Among the many Natural Language Processing (NLP) tasks, stemming is an important task in which the root or base form of the word is extracted. To the best of our knowledge, no work on stemming has been reported for this language. This work is a preliminary step towards building stemmer for Tenyidie Language. In our work, we reviewed the affixation rules for the Tenyidie language, using which we built 1,206 suffix combinations and 11 prefixes. We used a root word dictionary of 766 unique words and the generated affixes to build a stemmer for the Tenyidie Language. Our stemming approach achieved an accuracy of 60.69% on 430 inflected Tenyidie words.