Ditemukan 2 dokumen yang sesuai dengan query
Yudhistira Erlandinata
"Korpus relasi semantik dapat menunjang berbagai penelitian di bidang pengolahan bahasa manusia. Untuk Bahasa Indonesia, korpus relasi semantik yang berukuran besar dan berkualitas baik masih belum tersedia. Korpus relasi semantik dapat dibuat secara manual dengan melibatkan anotator dan juga dapat dihasilkan secara otomatis menggunakan algoritma rule-based atau machine learning. Penelitian ini bertujuan untuk mengevaluasiseberapa baik kualitas korpus relasi semantik Bahasa Indonesia, khususnya relasi hiponim-hipernim, apabila dibangun dengan pendekatan machine learning dan metode crowdsourcing yang menerapkan gamifikasi. Algoritma pattern-based yang sebelumnya pernah diteliti untuk Bahasa Indonesia akan digunakan untuk menghasilkan data training algoritma machine learning dan kandidat entri korpus untuk dianotasi dengan metode crowdsourcing. Kualitas korpus hasil metode crowdsourcing diukur berdasarkan tingkat persetujuan antar anotator dan diperoleh hasil yang cukup baik walaupun belum sempurna. Untuk pendekatan machine learning, beberapa model
machine learning yang diterapkan masih belum memberikan hasil optimal karena
keterbatasan resource.
Kata kunci: relasi semantik, hiponim-hipernim, crowdsourcing, gamifikasi, machine
learning, pattern-based
Semantic relations corpus is vital to support research in the field of Natural LanguageProcessing. Currently, there is no existing corpus of semantic relations in Indonesianlanguage which is enormous and high-quality. The corpus can be constructed manuallyby employing human annotators or built automatically using rule-based or machinelearning algorithms. This research aims to evaluate the quality of Indonesian hyponym-hypernym semantic relations corpus that is produced by crowdsourcing mechanism withgamification, and to test the model for semantic relations prediction using machinelearning algorithms. The pattern-based method is applied to obtain the training data formachine learning experiments and corpus entry candidates to be annotated using thecrowdsourcing method. The quality of the crowdsourced corpus is measured using inter-annotator agreement. The experimental result shows that the gamification-basedcrowdsourcing method is promising to produce the corpus. On the other hand, machinelearning models tested in this research have not given optimal results yet due to thelimitations of the lexical resources in Indonesian language."
Depok: Fakultas Ilmu Komputer Universitas Indonesia, 2021
S-pdf
UI - Skripsi Membership Universitas Indonesia Library
Voskuil, Jan
"
ABSTRAKThe central theme in this paper is the problem of shifting from natural language descriptions, as in traditional dictionaries and thesauri, to working IT (Information Technology) systems that support people carrying out their administrative tasks. An explicit description of the specific language used in an organization is necessary to guarantee properly working IT systems and a healthy flow of information. Traditionally, there are different ways of capturing such a vocabulary. Different options are considered, arguing that the general form of a thesaurus offers the optimal solution for a broad range of cases. Various requirements for such a thesaurus are examined. A real world example is discussed in some detail. Finally, the paper examines how modern Web technology can help optimizing the creation, management and use of enterprise thesauri. Using these technologies, the enterprise thesaurus can take up new roles in managing the information household of an organization."
University of Indonesia, Faculty of Humanities, 2015
909 UI-WACANA 16:2 (2015)
Artikel Jurnal Universitas Indonesia Library