International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 – 8958, Volume-9 Issue-1, October 2019 2577 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Retrieval Number: A9348109119/2019©BEIESP DOI: 10.35940/ijeat.A9348.109119 MT Embedded E-Learning in India - Challenges for NLP/AI Ritu Nidhi, Tanya Singh, D.K. Lobiyal Abstract -Indian languages are spoken by more than 90% of its population while most of the higher education happens in English medium. The policy makers in Indian government have realized that by introducing multilingual education electronically, they can reach out to the remotest corner of India and educate all in their mother tongue. The New Education Policy (NEP) draft just released by the government puts a heavy focus on mother tongues in education. The recent initiatives and focus on Natural Language Processing/ Artificial Intelligence (NLP/AI) in education through e-learning is not too surprising in this context. The paper presents the current initiatives in these directions by the government of India, surveys available NLP technologies particularly those for automatic translation of educational content developed by academia and industry and focuses on the Maithili language community. India's education needs are diverse and the success of e-learning depends heavily on the availability of necessary NLP tools in all languages. Almost all of major scheduled Indian languages are considered "resource-poor". While some of these languages may have the basic tools, they lack quality translation tools for delivering education in native language. The situation is more challenging in those languages where even the most basic resources and tools do not exist. Maithili - a language of Bihar and Nepal is such a language. The paper also presents an effort to develop MT resources and tools for Maithili and its application in delivering multilingual content for education. Keyword- E-learning, NLP, MT, Indian Language, Maithili I. INTRODUCTION India is one of the fastest growing markets in multilingual education technology because there is a need to reach out to the remotest regions of India covering a vast multilingual and socio cultural diversity. As per 2011 census report, there are 26 % of Indian population who are illiterate. The inherent socio cultural political diversity, exclusion, complexity etc in Indian education have been nicely presented by [1]. The potential growth, and opportunities for business has been summed up by [2], [3], and [4]. India's language scene can be described as follows - a vast multilingual and multicultural country with 22 national but resource poor languages and more than 1600 other languages with less that10 % English knowing population and significant illiteracy. This makes India a land of opportunities in the area of using language technology in education. Of the 22 scheduled languages, Hindi has the dual status of National and Official Language (NOL) and English as Associate Official Language (AOL). Revised Manuscript Received on October 15, 2019 Ritu Nidhi, scholar at Amity University, Noida, India Dr. Tanya Singh, Professor and Dy. Director (Academics), Amity School of Engineering & Technology, Amity University, Uttar Pradesh. Dr. DK Lobiyal, Professor, School of Computer & Systems Sciences, Jawaharlal Nehru University, New Delhi. All other 21 scheduled Indian languages enjoy national status but do not have sufficient language technology resources to compete with English. Factors like variability, language mixing, rich morphology, weak syntax, lack of technology standards have contributed to poor development of computer technologies in Indian languages. Maithili is one of the 22 schedule Indian languages spoken in the state of Bihar and neighboring Nepal and is extremely resource poor in terms of language technology resources. Lack of digital resources has resulted in a near absence of computer technologies in this language. A.Landscape of Maithili Maithili (ISO 639-3) is an Indo Aryan language spoken in Bihar and Nepal. It is also spoken in neighboring states of Jharkhand and West Bengal. As per the census of India (2011), we have more than 13 million Maithili speakers in India alone. Maithili is also spoken in the neighboring country Nepal where it is the second official language and the second most spoken language. A rough estimate puts the total number of Maithili speakers in the world to be around 34 million 1 . Popularly written in Devanagari, Maithili has its own script called Mithilakshara. Maithili literature dates back to 8th century AD and has at least six varieties [5]. Maithili shows typical linguistic features of an eastern Indo Aryan language. With a rich inflection system, absence of agreement at the level of verb and reasonable scrambling due to weaker syntax. Maithili has its unique features like varying layers of pronominal and verbal honorifics. Maithili has typical Indo Aryan Subject-Object-Verb (SOV) word order, however flexibility in moving syntactic constituents with relative ease poses challenges for automated linguistic analyses [5]. Indo Aryan languages of north India can easily be contrasted with English which is a rigid syntax SVO language with little scope for scrambling. English also exhibits weaker morphology compared to Maithili. These and other contrasting features of the two languages create difficulties for automatic translation. II. E-LEARNING IN INDIA India's education is based on the colonial model established by Lord Macaulay during the British administration of India. Successive post independence governments in India have tried their best to adapt it to Indian diversity, but were not successful given the complexity and challenges therein. The question of languages, medium of instruction etc have been more difficult to implement in India than the content. Though the literacy rates have risen sharply, still there is a massive 26% population below this threshold. The 2001 and 2011 Census Report published by Government of India present contrasting literacy figures. 1 https://www.ethnologue.com/language/mai