Sistem Pengubah Kalimat Bahasa Indonesia Ke Dalam Bentuk Parse Tree Menggunakan Metode Bottom-up Parsing
DOI:
https://doi.org/10.34818/eoe.v7i3.14222Abstract
Abstrak Natural Language Processing (NLP) adalah area dari penelitian interdisipliner yang memungkinkan komputer untuk berkomunikasi dengan manusia dengan cara yang sama seperti bagaimana manusia berkomunikasi dengan manusia lain. Salah satu tahapan dalam Natural Language Processing (NLP) adalah parsing. Parsing telah berkembang pesat meliputi cakupan yang luas, akurasi yang tinggi, dan efisiensi dalam beberapa periode terakhir. Banyak sekali penelitian sebelumnya yang telah berhasil mengubah sebuah kalimat dari berbagai bahasa ke dalam bentuk parse tree, tapi hanya sedikit untuk Bahasa Indonesia. Dalam rangka sarana pendukung berbagai aplikasi pengolah bahasa guna meningkatkan penelitian di bidang Natural Language Processing (NLP), maka parser Bahasa Indonesia diperlukan dan perlu dikembangkan keberadaannya. Pada penelitian tugas akhir ini, dibangun sebuah sistem untuk mengubah kalimat Bahasa Indonesia ke dalam bentuk parse tree dengan menggunakan metode Bottom-Up Parsing. Bentuk parse tree yang dihasilkan sistem ini dievaluasi pengujian performansi dengan menggunakan PARSEVAL metrics. Dengan total hasil pengujian didapatkan precision dan recall sebesar 40,94% dan 72,26%. Kata kunci : natural language processing, parsing, parse tree, bottom-up parsing, PARSEVAL. Abstract Natural Language Processing is an area of interdisciplinary research that enables computers to communicate with humans in the same way as humans communicate with other humans. One of the stages in Natural Language Processing is parsing. Parsing has developed rapidly covering wide, high accuracy, and efficiency in the last few periods. Many previous studies have succeeded in converting a sentence from various languages into the form of a parse tree, but only a little for Indonesian. In order to support various language processing applications and in order to enhance research in the field of Natural Language Processing, an Indonesian parser is needed and its existence needs to be developed. In this final project research, a system will be built to convert Indonesian sentences into parse tree form using the Bottom-Up Parsing method. The form of the parse tree produced by this system will be evaluated for performance testing using PARSEVAL metrics. With the total performance testing results obtained precision and recall of 40,94% and 71,59%. Keywords: natural language processing, parsing, parse tree, bottom-up parsing, PARSEVALDownloads
References
[1]Mark Johnson Matthew Lease, Eugene Charniak. Parsing and it’s application for conversational speech. Brown Laboratory for Linguistic Information Processing Brown University, 2005.
[2]Boumediene Belkhouche Maad Shatnawi. Parse trees of arabic sentences using the natural language toolkit. College of IT, UAE University, Al Ain, 2012.
[3]E. Brill. Some advances in rule-based part of speech tagging. AAAI-94 Proceedings, pages 722–727, 1994. [4]G. Satta H. Bunt, J. Carroll. New Developments In Parsing Technology. Springer, 2005.
[5]Sara Stymne. Treebank grammars and parser evaluation. Department of Linguistics and Philology, 2014.
[6]Rosa Ariani Sukamto. Penguraian bahasa indonesia dengan menggunakan pengurai collins. Master Thesis, Institut Teknologi Bandung, 2009.
[7]Holon Institute od Technology. Information system. http://www.hit.ac.il/staff/leonidm/ information-systems/ch68.html, 2012. Online; Accessed 29 July 2020.
[8]Alexander Gelbukh. Special issue: Natural language processing and its applications. Instituto Polite´cnico Nacional Centro de Investigacio´ n en Computacio´ n Me´xico, Mexico, 2010.
[9]J. E. Schmidt, F. L. The validity and utility of selection methods in personnel psychology: Practica and theoretical implications of 85 years of research findings. Springer, 1998.
[10]Xiaojun Wan Meichun Liu Weiwei Sun, Yufei Chen. Parsing chinese sentences with grammatical relations. Institute of Computer Science and Technology and Center for Chinese Linguistics, City University of Hong Kong Department of Linguistics and Translation, 2018.
[11]Elisa Margareth Sibarani. A study of parsing process on natural language processing in bahasa indonesia.
IEEE 16th International Conference on Computational Science and Engineering, 2013.
[12]Alejandro Pazos Juan Ram o´ n Rabun˜ al Dopico, Julian Dorado. Rule Engines and Agent-Based Systems. IGI Global, 2008.
[13]James Suciadi. Studi analisis metode-metode parsing dan interpretasi semantik pada natural language pro- cessing. Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Kristen Petra, 2001.
[14]NLP-progress. Automatic parser evaluation. http://nlpprogress.com/english/constituency_
parsing.html. Online; Accessed 1 August 2020.
[15]M. Arimura. A grammar-based compression using a variation of chomsky normal form of context free grammar. In 2016 International Symposium on Information Theory and Its Applications (ISITA), pages 246–250, October 2016.
[16]S. Lappin A. Clark, C. Fox. The handbook of computational linguistics and natural language processing. In Blackwell Handbooks, Linguistics, October 2010.
[17]A. D. Gaikwad R. C. Dharmik, R. S. Bhanuse. Ambiguity of context free grammar using the cyk algorithm. In 2016 World Conference on Futuristic Trends in Research and Innovation for Social Welfare (Startup Conclave), pages 1–6, February 2016.
[18]J. D. Ullman J. E. Hopcroft. Introduction to automata theory, languages, and computation. Addison-Wesley
Longman Publishing Co., Inc., Boston, MA, USA, page 1st Edition, 1990.
[19]P. Barabs L. Kovcs. Experiences in building of context-free grammar tree. In 2011 IEEE 9th International Symposium on Applied Machine Intelligence and Informatics (SAMI), pages 67–71, January 2011.
[20]K. Katz R. MacIntyre A. Bies, M. Ferguson. Bracketing guidelines for treebank ii style penn treebank project. http://catalog.ldc.upenn.edu/docs/LDC99T42/prsguid1.pdf, 1995. Online; Accessed 30 June 2020.
[21]Habash N. Introduction to arabic natural language processing. Morgan Claypool Publishers, 2010. [22]Josef van Genabith Ines Rehbein. Evaluating evaluation measures. NODALIDA 2007 Conference Procee- dings, pp. 372–379, 2007.
[23]Flickinger Ezra Black, Steve Abney. A procedure for quantitatively comparing the syntactic coverage of english grammarss. Proceedings of the 1991 DARPA Speech and Natural Language Workshop, 1991.
[24]Arawinda Dinakaramani Farm Rashel Ruli Andry Luthfi. Indonesian pos tagged corpus. http://bahasa. cs.ui.ac.id/treebank/corpus, 2017. Online; Accessed 20 May 2020.
[25]Dr. Sarmad Hussain. Pan localization. http://www.panl10n.net/, 2010. Online; Accessed 5 August 2020.
[26]V. Gurusamy. Preprocessing techniques for text mining. Conference Paper RTRICS, India, 2014.
[27]D. Manning. Introduction to information retrieval. Cambridge University Press New York, NY, USA, 2008. [28]Philipp Koehn. Advanced natural language processing lecture 17 statistical parsing ii. http://www.inf.
ed.ac.uk/teaching/courses/anlp/slides/anlp14b-2x2.pdf, 2013. Online; Accessed 15 July 2020.
[29]Indiana University Dept. of Linguistics. Parser evaluation. https://wiki.eecs.yorku.ca/course_ archive/2014-15/W/6339/_media/10e-eval-2x3.pdf, 2009. Online; Accessed 15 July 2020.
[30]Margus Treumuth Taavet Kikas. Constituency parsing. http://kodu.ut.ee/~treumuth/NLP/syntax. pdf, 2007. Online; Accessed 20 July 2020.



