Parsing Indonesian Syntactic with Recursive Neural Network

Karisma Trinanda Putra, Djoko Purwanto, Ronny Mardiyanto

Abstract


Sentence is a form of human communication which is closely related to language system. Sentence is one of the recursive structures that are often found in daily conversation. Learning syntactic structure is useful to explore the meaning of the sentence contained on it or translated it into another language such as machine language. The problem is meaning, ambiguity, and the language that is not according to the rules of syntax, causing the command translation become more complex. This research is about parsing Indonesian syntax based on natural language rules for applications in the field of human-machine interaction. Each word that is a part of the sentence, is mapped into vector-space model. To estimate the potential connection of two words, we use the recursive neural network. The potential connection of two words translated into a higher structure to obtain a complete sentence structure. We obtain 93% accuracy, with 50 data-set are given in the learning process to represent a hundred vocabularies.

Keywords


Natural language processing; vector-space model; recursive neural network

Full Text:

PDF

References


S. Richard, B. John, M. Christopher, N. Andrew, "Parsing with compositional vector grammars", Proceedings of the ACL conference. 2013.

Yoshua, D. Réjean, V. Pascal, J. Christian, “A Neural Probabilistic Language Model” Journal of Machine Learning Research 3 1137–1155. 2003.

S. Richard, C. Chiung-Yu Lin, Y. Andrew, M. Christopher, “Parsing Natural Scenes and Natural Language with Recursive Neural Networks”, Proceedings of the 26th International Conference on Machine Learning (ICML). 2011.

Ronan, W. Jason, B. L´ eon, K. Michael, K. Koray, K. Pavel “Natural Language Processing (Almost) from Scratch” Journal of Machine Learning Research 12. 2011.

Danqi and M. Christopher “A Fast and Accurate Dependency Parser using Neural Networks” Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014.




DOI: http://dx.doi.org/10.12962/j23546026.y2015i1.1050

Refbacks

  • There are currently no refbacks.


View my Stat: Click Here

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.