A Positive-Unlabeled Learning Model for Extending a Vietnamese Petroleum Dictionary based on Vietnamese Wikipedia Data
Authors | Ngoc Trinh Vu Quoc-Dat Nguyen Tien-Dat Nguyen Manh-Cuong Nguyen Van-Vuong Vu Quang-Thuy Ha |
|---|---|
Publication date | 2018 |
DOI | 10.1007/978-3-319-75417-8_18 |
Links | Original |
A Positive-Unlabeled Learning Model for Extending a Vietnamese Petroleum Dictionary based on Vietnamese Wikipedia Data - scientific work related to Wikipedia quality published in 2018, written by Ngoc Trinh Vu, Quoc-Dat Nguyen, Tien-Dat Nguyen, Manh-Cuong Nguyen, Van-Vuong Vu and Quang-Thuy Ha.
Overview
This study provides a positive-unlabeled learning model for extending a Vietnamese petroleum dictionary based on Vietnamese Wikipedia data. Machine learning algorithms with positive and unlabeled data together with separated and combined between Google similarity distance and Cosine similarity distance, used in this study. The data sources used to integrate are English - Vietnamese oil and gas dictionary and the Vietnamese Wikipedia. In the results, a novelty way for data integration with higher accuracy by using a combination of algorithms. The first Vietnamese oil and gas ontology was built in Vietnam. This ontology is a useful tool for staff in the oil and gas industry in training, research, search daily.
