Analisis Part Of Speech (POS) Tagging menggunakan metode HMM Trigram pada data Al-Qur'an

Al-Hamro, Izki Zakiyah (2021) Analisis Part Of Speech (POS) Tagging menggunakan metode HMM Trigram pada data Al-Qur'an. Diploma thesis, UIN Sunan Gunung Djati Bandung.

[img]
Preview
Text (COVER)
1_cover.pdf

Download (138kB) | Preview
[img]
Preview
Text (ABSTRAK)
2_abstrak.pdf

Download (177kB) | Preview
[img]
Preview
Text (DAFTAR ISI)
3_daftarisi.pdf

Download (96kB) | Preview
[img]
Preview
Text (BAB I)
4_bab1.pdf

Download (133kB) | Preview
[img] Text (BAB II)
5_bab2.pdf
Restricted to Registered users only

Download (446kB) | Request a copy
[img] Text (BAB III)
6_bab3.pdf
Restricted to Registered users only

Download (389kB) | Request a copy
[img] Text (BAB IV)
7_bab4.pdf
Restricted to Registered users only

Download (462kB) | Request a copy
[img] Text (BAB V)
8_bab5.pdf
Restricted to Registered users only

Download (99kB) | Request a copy
[img] Text (DAFTAR PUSTAKA)
9_daftarpustaka.pdf
Restricted to Registered users only

Download (118kB) | Request a copy

Abstract

Part Of Speech (POS) tagging merupakan bagian dari Natural Language Processing untuk menetukan dengan benar label kata pada suatu kalimat dari input yang diberikan. Teknik POS tagging yang berbeda dalam beberapa literatur telah dikembangkan untuk teks bahasa Inggris, dan sedikit untuk teks bahasa Arab. Permasalahan ini menggunakan metode yang didasarkan pada model Markov tersembunyi kedua, yaitu mencari dua kata ke masa lalu atau lebih dikenal dengan sebutan metode HMM Trigram. Masalah utama POS tagging adalah Out Of Vocabulary (OOV) dan ambiguitas kata. Penelitian ini membahas POS tagging menggunakan metode HMM Trigram pada data teks Al-Qur’an. Dataset terbagi menjadi tiga kategori data yang berasal dari quran corpus terdiri dari 150 kalimat sempurna sederhana, 50 kalimat dengan S/P/O/K lebih dari satu dan 50 ayat Al-Qur’an pilihan. Percobaan data dilakukan dengan teknik validasi silang yaitu k-fold cross validation. Data diklasifikasi menjadi dua, yaitu data latih dan data uji. Data latih digunakan untuk mencari probabilitas emisi dan transisi, sedangkan pengujian data menggunakan algoritma Viterbi. Hasil percobaan mencapai akurasi rata-rata sebesar 86% untuk dataset sederhana, 60% untuk dataset sedang, dan 38% untuk dataset ayat lengkap. Part Of Speech (POS) tagging is part of Natural Language Processing to determine the word label correctly in a sentence from the input given. The different POS tagging techniques have been developed in some literature for English text, and a little for Arabic text. This problem uses a method based on the second hidden Markov model, which is looking for two words from the past or as known as the HMM Trigram method. The main problems with POS tagging are Out Of Vocabulary (OOV) and word ambiguity. This study discusses POS tagging using the HMM Trigram method on Al-Qur'an text data. The dataset is divided into three categories of data derived from the quran corpus consisting of 150 simple perfect sentences, 50 sentences with more than one S/P/O/K and 50 selected verses of the Qur'an. The data experiment was carried out by using cross validation technique, namely k-fold cross validation. The data is classified into two, those are training data and test data. The training data is used to find the emission and transition probabilities, while the data testing uses the Viterbi algorithm. The experimental results achieved an average accuracy of 86% for the simple dataset, 60% for the medium dataset, and 38% for the complete verses dataset.

Item Type: Thesis (Diploma)
Uncontrolled Keywords: Part Of Speech Tagging; Metode HMM Trigam; Algoritma Viterbi;
Subjects: Mathematics > Data Processing and Analysis of Mathematics
Applied mathematics > Programming Mathematics
Divisions: Fakultas Sains dan Teknologi > Program Studi Matematika
Depositing User: Izki Zakiyah Al-Hamro
Date Deposited: 19 Mar 2021 06:03
Last Modified: 19 Mar 2021 06:03
URI: https://digilib.uinsgd.ac.id/id/eprint/37929

Actions (login required)

View Item View Item