Building Balinese Part-of-Speech Tagger Using Hidden Markov Model (HMM)

2020 ◽  
Vol 9 (2) ◽  
pp. 303
Author(s):  
I Gde Made Hendra Pradiptha ◽  
Ngurah Agus Sanjaya ER
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Probabilistic Approach ◽  
Word Class ◽  
Part Of Speech Tagging ◽  
Part Of Speech ◽  
Fast Processing ◽  
Pos Tagger ◽  
Speech Tagging

Part-of-Speech tagging or word class labeling is a process for labeling a word class in a word in a sentence. Previous research on POS Tagger, especially for Indonesian, has been done using various approaches and obtained high accuracy values. However, not many researchers have built POS Tagger for Balinese. In this article, we are interested in building a POS Tagger for Balinese using a probabilistic approach, specifically the Hidden Markov Model (HMM). HMM is selected to deal with ambiguity since it gives higher accuracy and fast processing time. We used k-fold cross-validation (with k = 10) and tagged corpus around 3669 tokens with 21 tags. Based on the experiments conducted, the HMM method obtained an accuracy of 68.56%.

POS Tagging Bahasa Indonesia Dengan HMM dan Rule Based

2013 ◽  
Vol 8 (2) ◽  
Author(s):  
Kathryn Widhiyanti ◽  
Agus Harjoko
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Word Class ◽  
Rule Based ◽  
Part Of Speech Tagging ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Class Labelling ◽  
Speech Tagging

The research conduct a Part of Speech Tagging (POS-tagging) for text in Indonesian language, supporting another process in digitising natural language e.g. Indonesian language text parsing. POS-tagging is an automated process of labelling word classes for certain word in sentences (Jurafsky and Martin, 2000). The escalated issue is how to acquire an accurate word class labelling in sentence domain. The author would like to propose a method which combine Hidden Markov Model and Rule Based method. The expected outcome in this research is a better accurary in word class labelling, resulted by only using Hidden Markov Model. The labelling results –from Hidden Markov Model– are  refined by validating with certain rule, composed by the used corpus automatically. From the conducted research through some POST document, using Hidden Markov Model, produced 100% as the highest accurary for identical text within corpus. For different text within the referenced corpus, used words subjected in corpus, produced 92,2% for the highest accurary.

scholarly journals Pelabelan Kelas Kata Bahasa Jawa Menggunakan Hidden Markov Model

2020 ◽  
Vol 2 (2) ◽  
pp. 71-83
Author(s):  
Mohammad Mursyit ◽  
Aji Prasetya Wibawa ◽  
Ilham Ari Elbaith Zaeni ◽  
Harits Ar Rosyid
Keyword(s):  
Short Stories ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Part Of Speech Tagging ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Improve Accuracy ◽  
Unknown Words ◽  
Speech Tagging

Part of Speech Tagging atau POS Tagging adalah proses memberikan label pada setiap kata dalam sebuah kalimat secara otomatis. Penelitian ini menggunakan algoritma Hidden Markov Model (HMM) untuk proses POS Tagging. Perlakuan untuk unknown words menggunakan Most Probable POS-Tag. Dataset yang digunakan berupa 10 cerita pendek berbahasa Jawa terdiri dari 10.180 kata yang telah diberikan tagsetBahasa Jawa. Pada penelitian ini proses POS Tagging menggunakan dua skenario. Skenario pertama yaitu menggunakan algoritma Hidden Markov Model (HMM) tanpa menggunakan perlakuan untuk unknown words. Skenario yang kedua menggunakan HMM dan Most Probable POS-Tag untuk perlakuan unknown words. Hasil menunjukan skenario pertama menghasilkan akurasi sebesar 45.5% dan skenario kedua menghasilkan akurasi sebesar 70.78%. Most Probable POS-Tag dapat meningkatkan akurasi pada POS Tagging tetapi tidak selalu menunjukan hasil yang benar dalam pemberian label. Most Probable POS-Tag dapat menghilangkan probabilitas bernilai Nol dari POS Tagging Hidden Markov Model. Hasil penelitian ini menunjukan bahwa POS Tagging dengan menggunakan Hidden Markov Model dipengaruhi oleh perlakuan terhadap unknown words, perbendaharaan kata dan hubungan label kata pada dataset.  Part of Speech Tagging or POS Tagging is the process of automatically giving labels to each word in a sentence. This study uses the Hidden Markov Model (HMM) algorithm for the POS Tagging process. Treatment for unknown words uses the Most Probable POS-Tag. The dataset used is in the form of 10 short stories in Javanese consisting of 10,180 words which have been given the Javanese tagset. In this study, the POS Tagging process uses two scenarios. The first scenario is using the Hidden Markov Model (HMM) algorithm without using treatment for unknown words. The second scenario uses HMM and Most Probable POS-Tag for treatment of unknown words. The results show that the first scenario produces an accuracy of 45.5% and the second scenario produces an accuracy of 70.78%. Most Probable POS-Tag can improve accuracy in POS Tagging but does not always produce correct labels. Most Probable POS-Tag can remove zero-value probability from POS Tagging Hidden Markov Model. The results of this study indicate that POS Tagging using the Hidden Markov Model is influenced by the treatment of unknown words, vocabulary and word label relationships in the dataset.

Sign in / Sign up

Export Citation Format

Share Document