Record Details

Parsing struktur semantik soal cerita matematika berbahasa indonesia menggunakan recursive neural network

Register: Jurnal Ilmiah Teknologi Sistem Informasi

View Archive Info
 
 
Field Value
 
Title Parsing struktur semantik soal cerita matematika berbahasa indonesia menggunakan recursive neural network
 
Creator Prasetya, Agung
Fatichah, Chastine
Yuhana, Umi Laili
 
Subject parsing; pohon biner; Recursive Neural Network; soal cerita; struktur semantik; binary tree; math word problem; semantic structure
 
Description Soal cerita berperan penting untuk kemajuan pengembangan kecerdasan buatan. Hal ini karena penyelesaian soal cerita melibatkan pengembangan sebuah sistem yang mampu memahami bahasa alami. Pembentukan sistem penyelesaian soal memerlukan mekanisme untuk mendekomposisikan teks soal ke segmen-segmen teks untuk diterjemahkan ke jenis operasi hitung. Segmen-segmen tersebut ditentukan melalui proses parsing semantik struktur soal agar menghasilkan segmen-segmen yang maknanya menunjuk operasi hitung. Sejumlah metode usulan saat ini sesuai untuk diterapkan pada soal cerita berbahasa Inggris dan belum diterapkan pada soal cerita berbahasa Indonesia. Dampaknya adalah segmen-segmen yang dihasilkan belum tentu menghasilkan urutan pengerjaan operasi yang sesuai makna cerita. Penelitian ini mengusulkan penggunaaan Recursive Neural Network (RNN) sebagai parser struktur semantik soal cerita berbahasa Indonesia. Pengujian parser struktur semantik soal dilakukan terhadap soal-soal yang berasal dari Buku Sekolah Elektronik (BSE) Sekolah Dasar (SD) dari Pusat Perbukuan Kementerian Pendidikan dan Kebudayaan. Hasil pengujian menunjukkan akurasi akhir sebesar 86,4%.  Math word problems play an important role for the development of artificial intelligent. This is because solving word problems involves the development of a system that can understand natural language.  Designing a system for solving math word problems requires a mechanism for decomposing a text into segments of text to be translated into math operation. The segments are categorized through the process of parsing the semantic structure of the word problems to obtain segments whose meanings refer to math operation. A number of current proposed methods are suitable to be applied to English math word problems and have never been applied to Indonesian math word problems. The impact is that the segments produced are not necessarily in line with the sequences of operations appropriate with the meaning of the story.  This study proposed the use of Recursive Neural Network (RNN) as a parser of semantic structure of Indonesian math word problems. The testing of the parser was carried out on the math word problems taken from the Elementary School’s Electronic School Book  (BSE) published by the Book Center of the Ministry of Education and Culture. The result of the testing showed that the final accuracy was 86.4%.
 
Publisher Information Systems - Universitas Pesantren Tinggi Darul Ulum
 
Contributor —
 
Date 2019-06-27
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Peer-reviewed Article
 
Format application/pdf
 
Identifier https://journal.unipdu.ac.id/index.php/register/article/view/1537
10.26594/register.v5i2.1537
 
Source Register: Jurnal Ilmiah Teknologi Sistem Informasi; Vol 5, No 2 (2019): July; 106-115
Register: Jurnal Ilmiah Teknologi Sistem Informasi; Vol 5, No 2 (2019): July; 106-115
2502-3357
2503-0477
10.26594/register.v5i2
 
Language eng
 
Relation https://journal.unipdu.ac.id/index.php/register/article/view/1537/pdf
 
Rights Copyright (c) 2019 Register: Jurnal Ilmiah Teknologi Sistem Informasi
http://creativecommons.org/licenses/by/4.0