No abstract

No abstract

Part-of-speech tagging is a process of assigning each word of a sentence to a part of speech based on its context and definition. POS tagging is a prerequisite tool for many NLP tasks like word sense disambiguity, name entity information extraction, etc. Unfortunately, very little work has been done so far in this line for Khasi Language. The main difficulty lies with the unavailability of an annotated corpus. Hence, a small corpus is created which consists of 778 sentences with 34,873 words, out of which 3,942 are distinct words and a tagset of 52 tags. In this chapter, three methods for POS tagging, namely Brill's tagger, hidden Markov model (HMM)-based tagger, and bidirectional long short-term memory recurrent neural network (Bi-LSTM), have been implemented. Then a comparative analysis is performed, and it is observed that Bi-LSTM performs better in terms of accuracy.

Part-of-speech (POS) tagging is one of the research challenging fields in natural language processing (NLP). It requires good knowledge of a particular language with large amounts of data or corpora for feature engineering, which can lead to achieving a good performance of the tagger. Our main contribution in this research work is the designed Khasi POS corpus. Till date, there has been no form of any kind of Khasi corpus developed or formally developed. In the present designed Khasi POS corpus, each word is tagged manually using the designed tagset. Methods of deep learning have been used to experiment with our designed Khasi POS corpus. The POS tagger based on BiLSTM, combinations of BiLSTM with CRF, and character-based embedding with BiLSTM are presented. The main challenges of understanding and handling Natural Language toward Computational linguistics to encounter are anticipated. In the presently designed corpus, we have tried to solve the problems of ambiguities of words concerning their context usage, and also the orthography problems that arise in the designed POS corpus. The designed Khasi corpus size is around 96,100 tokens and consists of 6,616 distinct words. Initially, while running the first few sets of data of around 41,000 tokens in our experiment the taggers are found to yield considerably accurate results. When the Khasi corpus size has been increased to 96,100 tokens, we see an increase in accuracy rate and the analyses are more pertinent. As results, accuracy of 96.81% is achieved for the BiLSTM method, 96.98% for BiLSTM with CRF technique, and 95.86% for character-based with LSTM. Concerning substantial research from the NLP perspectives for Khasi, we also present some of the recently existing POS taggers and other NLP works on the Khasi language for comparative purposes.

No abstract