A comprehensive survey on Indian regional language processing
- PDF / 1,473,070 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 83 Downloads / 239 Views
A comprehensive survey on Indian regional language processing B. S. Harish1 · R. Kasturi Rangan1 Received: 24 December 2019 / Accepted: 29 May 2020 © Springer Nature Switzerland AG 2020
Abstract In recent information explosion, contents in internet are multilingual and majority will be in the form of natural languages. Processing of these natural languages for various language processing tasks is challenging. The Indian regional languages are considered to be low resourced when compared to other languages. In this survey, the various approaches and techniques contributed by the researchers for Indian regional language processing are reviewed. The tasks like machine translation, Named Entity Recognition, Sentiment Analysis and Parts-Of-Speech tagging are reviewed with respect to Rule, Statistical and Neural based approaches. The challenges which motivate to solve language processing problems are presented. The sources of dataset for the Indian regional languages are described. The future scope and essential requirements to enhance the processing of Indian regional languages for various language processing tasks are discussed.ϖ Keywords Language processing · Machine translation · Named entity recognition · POS tagging
1 Introduction Any language that has evolved naturally in humans through its usage over the time is called natural language. People exchange their knowledge, emotions and feelings with others through the means of natural language. There are different native languages existing in various parts of the world, each with its own alphabet, signs and grammar. If there is a nation where old and morphologically rich varieties of regional languages exist that is India [57]. It is comparatively easy for computers to process the data represented in English language through standard ASCII codes than other natural languages. However, building the machines capability of understanding other natural languages is arduous and is carried out using various techniques. There are many research works and applications like (1) Chatbot (2) Text-to-speech conversion (3) Language Identification (4) Hands-free computing (5) Spell-check (6) Summarizing-electronic medical records (7) Sentiment Analysis and so on, developed to handle these natural languages for real time needs. In this paper,
various methods used to develop the aforementioned applications; especially on Indian Regional Languages (IRL) are presented. Nowadays, the internet is no more monolingual; contents of the other regional languages are growing rapidly. According to the 2001 census, there are approximately 1000 documented languages and dialects in India. Much research is being carried out to facilitate users to work and interact with computers in their own regional natural languages [3]. Google offers searching in 13 languages and provides transliteration in Indian Regional languages (IRL) like Kannada, Hindi, Bengali, Tamil, Telugu, Malayalam, Marathi, Punjabi, and Gujarati [51]. The major concentrated tasks on IRL are Machine Translation (MT), Sentiment An
Data Loading...
