Natural Language Generation Scope, Applications and Approaches Manu Madhavan I st Semester M. Tech Computational Linguistics, Department of Computer Science and Engineering, Govt. Engg. College, Sreekrishnapuram, Palakkad, India-678633 E-mail: mmnamboodiry@gmail.com Abstract— Natural Language Generation is a subfield of com- putational linguistic that is concerned with the computer systems which can produce understandable texts in some human lan- guages. The system uses machine understandable logical form as input and produces syntactically and semantically valid sentences in natural language. The different stages of NLG include Content selection, Lexical selection, Sentence structuring and Discourse planning. The applications of NLG include text summarization, machine translation and question answering. The effectiveness of the NLG depends on the efficiency of internal knowledge representation. An ontology based Knowledge representation will improve the output text quality. This work also discusses the scope of applying Karaka relations in language modeling for NLG. Keywords—Natural Language Generation (NLG), Karaka Re- lations, Knowledge Representation. I. INTRODUCTION Natural language Generation(NLG) is a NLP task of gener- ating sentence from word knowledge and information provided in a logical representation.NLG is the fascinating area of research and emerging technology with many real world applications. A sentence is an abstract notion of an idea. The capability of a system to generate a meaningful sentence indicates its intelligence to generate an idea. Natural Language Generation is the inverse of natural language understanding (NLU). NLG maps from meaning to text, while NLU maps from text to meaning. The input to NLG system varies widely from one application to another. But, in NLU, all the texts are governed by relatively common grammar. NLU has been characterized by ambiguity, under- specification and ill-formed input. On the other hand, the non- linguistic input to the NLG system is relatively unambiguous, well-specified and well-formed [9]. The most of the NLG system follow a method of accepting some internal representation as an input and produce a natural language output. So, the problem of NLG is twofold [6]: • Selecting a Knowledge Representation(KR) • Transforming the information to Natural language(NL) The major question in NLG is how one can produce high quality natural text from some computer internal representa- tion of information. The effectiveness of this representation in- volves the understandability of the embodied information. The major task involved here is the designing of an unambiguous representation of world knowledge. The Indian language San- skrit has a systematic approach meant for cognitive knowledge description. This work analyses the scope and implementation issues of Natural Language Generation, its applications and a Karaka based input representation for NLG. A. System Definition Natural language generation is the process of converting an input knowledge representation into an expression is natural language(either text or speech) according to the application. The input to the system is a four tuple [8]: (K,C,U,D) where K is the knowledge source, a database of world knowledge. C is the communication goal, specified as independent of language which is using. U is the user model based on which the system is working. Probabilistic models are most commonly used in generation process. Finally, D is the discourse history, which deals with the ordering of information in the output text. The output will be natural language text which can be followed by a speech synthesizer according to the application. II. RELATED WORK An Ontology based multilingual sentence generator [13] for English, Spanish, Japanese and Chinese was a combination of example based, rule based and statistical components. This also provided an application-driven generation of sentences by feature based grammars.. SimpleNLG [1] is a realization engine for English which aims to provide simple and robust interfaces to generate syntactic structures and linearize them.. John A Batesman suggested a Systemic Functional Gram- mar (SFG) for representing the semantic features of a sentence. Based on SFG, a system network is developed and used as an internal representation for NLG [8]. In automatic story generator using Ontology [7] a rule based model generates the language and Ontology based internal representation check the semantic and pragmatic existence of the generated sentence. Rick Briggs suggested Sanskrit as a language for unam- biguous knowledge representation for Artificial Intelligent. In his paper he shows the clear parallelism between the semantic network and the way in which ancient Indian Grammarians performed the NLP [12].