Perbandingan Algoritma Conditional Random Field dan Hidden Markov Model pada Pos Tagging Bahasa Indonesia

Singgih Briandoko
Atika Ratna Dewi
Muhammad Akbar Setiawan

Teknikom: Teknologi Informasi, Ilmu Komputer dan Manajemen
Vol 2 No 2 (2018): Teknikom Vol. 2 No. 2 Tahun 2018

Twitter is now an alternative source of real timeinformation for the public. Technological developmentscover all aspects of life, one of which is the field of language.Natural Language Processing (NLP) devices developed tosupport those needs are POS Tagger. This research use 10tweets and HMM algorithm get 62,7% accuracy level whileConditional Random Field algorithm get 71%. This showsthat CRF is better for performing POS tagging in Indonesianon Twitter. HMM and CRF can handle tagging of words thatare not in the corpus but the results are not very good.