lisensi ini mengizinkan setiap orang untuk menggubah ...kc.umn.ac.id/5069/7/halaman awal.pdfkumpulan...

Team project ©2017 Dony Pratidana S. Hum | Bima Agus Setyawan S. IIP

Hak cipta dan penggunaan kembali:

Lisensi ini mengizinkan setiap orang untuk menggubah, memperbaiki, dan membuat ciptaan turunan bukan untuk kepentingan komersial, selama anda mencantumkan nama penulis dan melisensikan ciptaan turunan dengan syarat yang serupa dengan ciptaan asli.

Copyright and reuse:

This license lets you remix, tweak, and build upon work non-commercially, as long as you credit the origin creator and license it on your new creations under the identical terms.

IMPLEMENTASI BIGRAM MODEL DAN MARKOV CHAIN

DALAM ADD-IN MICROSOFT WORD UNTUK

MEMBENTUK KALIMAT BAHASA INGGRIS

DARI BAG OF WORDS

SKRIPSI

Diajukan sebagai salah satu syarat untuk memperoleh gelar

Sarjana Komputer (S.Kom.)

Disusun Oleh

Randy D’nata Prayogo

13110110017

PROGRAM STUDI INFORMATIKA

FAKULTAS TEKNIK DAN INFORMATIKA

UNIVERSITAS MULTIMEDIA NUSANTARA

TANGERANG

2018

Implementasi Bigram Model..., Randy D’nata Prayogo, FTI UMN, 2018

Scan by Easy Scanner


vii

JUDUL: IMPLEMENTASI BIGRAM MODEL DAN MARKOV CHAIN

DALAM ADD-IN MICROSOFT WORD UNTUK MEMBENTUK

KALIMAT BAHASA INGGRIS DARI BAG OF WORDS

ABSTRAK

.

Sebuah penelitian yang dilakukan Wijayanti pada tahun 2015 mengungkapkan

bahwa siswa di Mondial School masih membutuhkan bantuan dalam menulis

efektif. Walaupun di sekolah tersebut para siswa aktif berkomunikasi

menggunakan bahasa Inggris, kemampuan mereka tidak membantu dalam

mengerjakan tugas tertulis. Di sisi lain, aplikasi Microsoft Word adalah salah satu

aplikasi yang paling populer di antara pelajar, akan tetapi masih banyak pelajar

yang mengalami kesulitan dalam merangkai kalimat. Oleh karena itu dibuatlah

sebuah add-in Microsoft Word untuk membantu membentuk kalimat dari kata

acak. Add-in yang dibangun menggunakan konsep n-gram model dengan jumlah n

sama dengan dua. Dalam proses validasi yang telah dilakukan, 56 dari 100

kumpulan kata acak berhasil dibuat menjadi kalimat dalam bahasa Inggris yang

bersifat grammatically correct dan 48 di antara kalimat-kalimat tersebut dapat

dikategorikan sebagai logically correct.

Kata Kunci : N-Gram, Markov Chain, Pembentuk Kalimat, Bahasa Inggris, C#,

Visual Studio Tools for Office.


viii

TITLE: IMPLEMENTATION OF BIGRAM MODEL AND MARKOV

CHAIN FOR GENERATING ENGLISH SENTENCES FROM BAG OF

WORDS IN MICROSOFT WORD ADD-IN

ABSTRACT

In 2015, Wijayanti did a case study on students in Mondial School and revealed

that the students still need help in writing effectively. Despite the student‟s

English ability in oral communication, it doesn‟t help them in their writing

assignments. Incidentally, Microsoft Word is one of the most popular application

among students. However, the students still need outside help to form proper

sentences. Therefore the add-in was made to help forming sentences from bag of

words. The add-in implements n-gram model with the number of n equals two. In

the validation process, 56 of the 100 bag of words were made into proper

grammatically correct English sentences. Out of those 56 sentences, 48 of them

could be categorized as logically correct.

Keywords : N-Gram, Markov Chain, Sentence Generation, English Language, C#,

Visual Studio Tools for Office.


ix

DAFTAR ISI

LEMBAR PENGESAHAN SKRIPSI .................................................................... ii

PERNYATAAN TIDAK MELAKUKAN PLAGIAT .......................................... iii

PERNYATAAN PERSETUJUAN PUBLIKASI KARYA ILMIAH UNTUK

KEPENTINGAN AKADEMIS ............................................................................. iv

KATA PENGANTAR ............................................................................................ v

ABSTRAK ............................................................................................................ vii

ABSTRACT ......................................................................................................... viii

DAFTAR ISI .......................................................................................................... ix

DAFTAR GAMBAR ............................................................................................. xi

DAFTAR TABEL ................................................................................................ xiii

BAB I PENDAHULUAN ....................................................................................... 1

1.1. Latar Belakang Masalah ............................................................................. 1

1.2. Rumusan Masalah ...................................................................................... 4

1.3. Batasan Masalah......................................................................................... 4

1.4. Tujuan Penelitian ....................................................................................... 5

1.5. Manfaat Penelitian ..................................................................................... 5

1.6. Sistematika Penulisan ................................................................................ 5

BAB II LANDASAN TEORI ................................................................................. 7

2.1. Tenses ......................................................................................................... 7

2.2 Natural Language Generation ................................................................... 10

2.3. N-Gram Model ......................................................................................... 12

2.4. Markov Chain .......................................................................................... 13

2.5. Visual Studio Tools for Office ................................................................. 14

2.6. Leipzig Corpora Collection ...................................................................... 15

BAB III METODOLOGI PENELITIAN DAN PERANCANGAN SISTEM ..... 16

3.1. Metodologi Penelitian .............................................................................. 16

3.2. Perancangan Sistem ................................................................................. 17

3.2.1. Use Case Diagram ........................................................................... 18

3.2.2. Activity Diagram ............................................................................. 19

3.2.3. Sequence Diagram .......................................................................... 23

3.2.4. Struktur Tabel.................................................................................. 27

3.2.5. Class Diagram ................................................................................. 28

3.2.6. Flowchart ........................................................................................ 31


x

3.2.7. Rancangan User Interface ............................................................... 35

BAB IV IMPLEMENTASI DAN PENGUJIAN .................................................. 37

4.1. Spesifikasi Sistem .................................................................................... 37

4.1.1. Perangkat Keras .............................................................................. 37

4.1.2. Perangkat Lunak.............................................................................. 37

4.1.3. Bahasa Pemrograman yang Digunakan .......................................... 37

4.2. Implementasi Aplikasi ............................................................................. 37

4.3. Implementasi Algoritma........................................................................... 41

4.3.1. Implementasi Menambah Corpus Baru ........................................... 41

4.3.2. Implementasi N-Gram untuk Melakukan Generate N-Gram ......... 42

4.3.3. Implementasi Markov Chain untuk Generate Kalimat ................... 44

4.4. Simulasi Algoritma .................................................................................. 47

4.4.1. Simulasi N-Gram Model ................................................................. 47

4.4.2. Simulasi Markov Chain .................................................................. 48

4.5. Hasil Validasi oleh Pakar ......................................................................... 50

BAB V SIMPULAN DAN SARAN ..................................................................... 54

5.1. Simpulan .................................................................................................. 54

5.2. Saran ......................................................................................................... 54

DAFTAR PUSTAKA ........................................................................................... 55

LAMPIRAN .......................................................................................................... 57


xi

DAFTAR GAMBAR

Gambar 2.1. Diagram Pipeline Architecture (Perera dan Nand, 2017:3) ............. 10 Gambar 2.2. Contoh Markov Chain ...................................................................... 14

Gambar 3.1. Use Case Diagram ........................................................................... 18 Gambar 3.2. Activity Melihat Corpora ................................................................. 19 Gambar 3.3. Activity Menambah Corpora Baru ................................................... 19 Gambar 3.4. Activity Melihat N-Gram .................................................................. 20 Gambar 3.5. Activity Melakukan Generate N-Gram ............................................ 21 Gambar 3.6. Activity Melakukan Generate Kalimat ............................................. 22 Gambar 3.7. Activity Melihat Tutorial .................................................................. 22 Gambar 3.8. Sequence Melihat Corpora .............................................................. 23 Gambar 3.9. Sequence Menambah Corpora Baru ................................................ 24

Gambar 3.10. Sequence Melihat N-Gram ............................................................. 24 Gambar 3.11. Sequence Melakukan Generate N-Gram........................................ 25 Gambar 3.12. Sequence Melakukan Generate Kalimat ........................................ 26 Gambar 3.13. Sequence Melihat Tutorial ............................................................. 27 Gambar 3.14. Class Diagram Bagian Pertama ..................................................... 28 Gambar 3.15. Class Diagram Bagian Kedua ........................................................ 29 Gambar 3.16. Class Diagram Bagian Ketiga ........................................................ 29 Gambar 3.17. Class Diagram secara keseluruhan ................................................ 30 Gambar 3.18. Flowchart Proses Melakukan N-Gram .......................................... 31 Gambar 3.19. Flowchart Proses Melakukan N-Gram (Lanjutan)......................... 32 Gambar 3.20. Flowchart Markov Chain ............................................................... 33 Gambar 3.21. Flowchart Validasi N-Gram untuk Markov Chain ........................ 34 Gambar 3.22. Rancangan Ribbon Utama .............................................................. 35

Gambar 3.23. Rancangan Form View Corpora ..................................................... 35 Gambar 3.24. Rancangan Form View N-Gram .................................................... 36 Gambar 3.25. Rancangan Form Generate Sentence.............................................. 36 Gambar 3.26. Rancangan Form Tutorial............................................................... 37 Gambar 4.1. Simulasi N-Gram ............................................................................. 48

Gambar 4.2. State Diagram dari tabel bigram ...................................................... 49

Gambar 4.3. Screenshot Constructor dan Pemicu Backgroundworker ................. 41 Gambar 4.4.Screenshot Potongan Kode untuk Menyimpan Corpus .................... 41 Gambar 4.5. Screenshot Potongan Kode untuk Menyimpan Corpus (Lanjutan) . 42 Gambar 4.6. Screenshot Potongan Kode untuk Melakukan Query Terhadap

Setiap Kalimat dan Truncate Tabel....................................................................... 42

Gambar 4.7. Screenshot Potongan Kode untuk Menangani Setiap Kalimat dalam

Corpus ................................................................................................................... 43 Gambar 4.8. Screenshot Potongan Kode untuk Melakukan Generate N-Gram ... 44

Gambar 4.9. Screenshot Potongan Kode untuk Mencari N-Gram yang

Berhubungan dengan Kata di Bag of Words ......................................................... 44

Gambar 4.10. Screenshot Potongan Kode untuk Mencari N-Gram yang

Berhubungan dengan Kata di Bag of Words (Lanjutan) ....................................... 45

Gambar 4.11. Screenshot Potongan Kode untuk Markov Chain .......................... 45 Gambar 4.12. Screenshot Potongan Kode untuk Markov Chain (Lanjutan) ........ 46 Gambar 4.13. Screenshot Potongan Kode untuk Markov Chain (Lanjutan) ........ 46


xii

Gambar 4.14. Ribbon Utama ................................................................................ 38 Gambar 4.15. Form View Corpora ....................................................................... 38 Gambar 4.16. Form Insert New Corpus ................................................................ 38 Gambar 4.17. Form View N-Gram ....................................................................... 39 Gambar 4.18. Form Generate N-Gram ................................................................. 39 Gambar 4.19. Form Generate Sentence ................................................................ 40 Gambar 4.20. Form Tutorial ................................................................................. 40


xiii

DAFTAR TABEL

Tabel 2.1. Daftar tugas setiap komponen pada pipeline architecture (Perera dan

Nand, 2017) ........................................................................................................... 11

Tabel 3.1. Struktur Tabel t_sentence..................................................................... 27 Tabel 3.2. Struktur Tabel t_ngram ........................................................................ 27 Tabel 4.1. Tabel Bigram........................................................................................ 48 Tabel 4.2. Tabel Hasil Validasi oleh Pakar ........................................................... 51


lisensi ini mengizinkan setiap orang untuk menggubah ...kc.umn.ac.id/5069/7/halaman awal.pdfkumpulan...

Documents