Prashant Chaudhary


2020

pdf bib
TREE ADJOINING GRAMMAR BASEDLANGUAGE INDEPENDENT GENERATOR
Pavan Kurariya | Prashant Chaudhary | Jahnavi Bodhankar | Lenali Singh | Ajai Kumar | Hemant Darbari
Proceedings of the 17th International Conference on Natural Language Processing (ICON)

This paper proposes language independent natural language generator for Tree Adjoining Grammar (TAG)[8] based Machine Translation System. In this model, the TAG based parsing and generation approach considered for the syntactic and semantic analysis of a source language. This model provides an efficient and a systematic way of encapsulating language resources with engineering solution to develop the machine translation System. A TAG based Generator is developed with existing resources using TAG formalism to generate the target language from TAG based parser derivation. The process allows syntactic feature-marking, the Subject-Predicate Agreement marking and multiple synthesized generated outputs in complex and morphological rich language. The challenge in applying such approach is to handle the linguistically diversified features. It is achieved using rule-based translation grammar model to align the source language to corresponding target languages. The computational experiments demonstrate that substantial performance in terms of time and memory could also be obtained by using this approach. Nevertheless, this paper also describes the process of lexicalization and explain the state charts, TAG based adjunction and substitution function and the complexity and challenges beneath parsing-generation process.