PARSING STRUKTUR PARAGRAF BERBASIS NEURAL NETWORK

Agung Prasetya
Taufiq Agung Cahyono


DOI: https://doi.org/10.29100/jipi.v7i2.2186

Abstract


Parsing paragraf memiliki peran penting dalam perkembangan kecerdasan buatan. Parsing menjadi langkah awal untuk menalar paragraf agar bisa dimengerti oleh mesin. Keefektifan metode parsing paragraf bergantung pada bagaimana mendekomposisikan teks ke segmen teks. Proses segmentasi tanpa memperhitungkan struktur semantik dari suatu paragraf akan menghasilkan struktur yang tidak sinkron dengan makna sebenarnya. Untuk mengatasi masalah ini, penelitian ini mengusulkan penerapan metode berbasis recursive neural network (RvNN). Metode ini berupaya mendapatkan binary tree terbaik yang merepresentasikan struktur paragraf. Metode usulan diterapkan untuk menyelesaikan paragraf-paragraf sederhana yaitu soal cerita anak. Hasil uji coba menunjukkan bahwa metode usulan dapat memparsing paragraf dengan tingkat akurasi sebesar 0.9. Metode usulan juga lebih efisien karena tidak perlu membuat repositori kerangka struktur

Keywords


paragraf, parsing; recursive neural network; semantik; binary tree;

Full Text:

PDF

Article Metrics :

References


P. Clark and O. Etzioni, My Computer Is an Honor Student But How Intelligent Is It? Standardized Tests as a Measure of AI, ojs.aaai.org, 2016, Accessed: Jun. 18, 2022. [Online]. Available: www.allenai.org

P. C.- AAAI and undefined 2015, Elementary school science and math tests as a driver for AI: Take the aristo challenge!, Citeseer, Accessed: Jun. 18, 2022. [Online]. Available: https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.697.9514&rep=rep1&type=pdf

L. Zhou, S. Dai, and L. Chen, Learn to Solve Algebra Word Problems Using Quadratic Programming, Association for Computational Linguistics, 2015. Accessed: Jun. 18, 2022. [Online]. Available: http://pan.baidu.com/

S. Roy, T. Vieira, and D. Roth, Reasoning about Quantities in Natural Language, Trans Assoc Comput Linguist, vol. 3, pp. 113, Dec. 2015, doi: 10.1162/tacl_a_00118.

A. Mitra and C. Baral, Learning To Use Formulas To Solve Simple Arithmetic Problems. Accessed: Jun. 18, 2022. [Online]. Availa-ble: http://allenai.org/euclid.html

R. Koncel-Kedziorski, H. Hajishirzi, A. Sabharwal, O. Etzioni, and S. D. Ang, Parsing Algebraic Word Problems into Equations, Trans Assoc Comput Linguist, vol. 3, pp. 585597, Dec. 2015, doi: 10.1162/tacl_a_00160.

Y. Wang, X. Liu, and S. Shi, Deep Neural Solver for Math Word Problems. Accessed: Jun. 18, 2022. [Online]. Available: https://aclanthology.org/D17-1088/

L. Wang et al., MathDQN: Solving Arithmetic Word Problems via Deep Reinforcement Learning. Accessed: Jun. 18, 2022. [Online]. Available: www.aaai.org

R. Socher et al., Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank, Association for Computational Linguistics. Accessed: Jun. 18, 2022. [Online]. Available: http://nlp.stanford.edu/

R. Socher, C. Chiung, Y. Lin, A. Y. Ng, and C. D. Manning, Parsing Natural Scenes and Natural Language with Recursive Neural Net-works, 2011. Accessed: Jun. 18, 2022. [Online]. Available: www.socher.org.

Y. Zhang, H. Zhou, and Z. Li, Fast and accurate neural CRF constituency parsing, in IJCAI International Joint Conference on Artifi-cial Intelligence, 2020, vol. 2021-January, pp. 40464053. doi: 10.24963/ijcai.2020/560.

T. Mikolov, K. Chen, G. Corrado, and J. Dean, Distributed Representations of Words and Phrases and their Compositionality. Ac-cessed: Jun. 18, 2022. [Online]. Available: https://proceedings.neurips.cc/paper/2013/hash/9aa42b31882ec039965f3c4923ce901b-Abstract.html

T. Mikolov, K. Chen, G. Corrado, and J. Dean, Efficient estimation of word representations in vector space, 2013.

R. Socher, J. Pennington, E. H. Huang, A. Y. Ng, and C. D. Manning, Semi-Supervised Recursive Autoencoders for Predicting Senti-ment Distributions. Accessed: Jun. 18, 2022. [Online]. Available: www.socher.org.

R. Socher, E. H. Huang, J. Pennington, A. Y. Ng, and C. D. Manning, Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection. Accessed: Jun. 18, 2022. [Online]. Available: https://proceedings.neurips.cc/paper/2011/hash/3335881e06d4d23091389226225e17c7-Abstract.html

B. Taskar, D. Klein, M. Collins, D. Koller, and C. Manning, Max-Margin Parsing. Accessed: Jun. 18, 2022. [Online]. Available: https://aclanthology.org/W04-3201.pdf

N. D. Ratliff, J. Andrew Bagnell, and M. A. Zinkevic, Maximum margin planning, in ACM International Conference Proceeding Series, 2006, vol. 148, pp. 729736. doi: 10.1145/1143844.1143936.

M. Odonnell, RSTTool 2.4-A Markup Tool for Rhetorical Structure Theory. Accessed: Jun. 18, 2022. [Online]. Available: https://aclanthology.org/W00-1434.pdf