Training Tree Adjoining Grammars with Huge Text Corpus Using Spark Map Reduce
2015
Tree adjoining grammars (TAGs) are mildly context sensitive formalisms used mainly in modelling natural languages. Usage and research on these psycho linguistic formalisms have been erratic in the past decade, due to its demanding construction and difficulty to parse. However, they represent promising future for formalism based NLP in multilingual scenarios. In this paper we demonstrate basic synchronous Tree adjoining grammar for English-Tamil language pair that can be used readily for machine translation. We have also developed a multithreaded chart parser that gives ambiguous deep structures and a par dependency structure known as TAG derivation. Furthermore we then focus on a model for training this TAG for each language using a large corpus of text through a map reduce frequency count model in spark and estimation of various probabilistic parameters for the grammar trees thereafter; these parameters can be used to perform statistical parsing on the trained grammar.
Keywords:
- Synchronous context-free grammar
- Machine learning
- Parsing
- Natural language processing
- Computer science
- L-attributed grammar
- Regular tree grammar
- Extended Affix Grammar
- Parsing expression grammar
- Top-down parsing
- Mildly context-sensitive grammar formalism
- Artificial intelligence
- Context-free grammar
- Ambiguous grammar
- Tree-adjoining grammar
- Programming language
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
12
References
2
Citations
NaN
KQI