Phân cụm từ Tiếng Việt và nhận diện từ trái nghĩa

• 主要作者: Nguyễn, Kim Anh
• 格式: Theses and Dissertations
• 語言: other
• 出版: Đại học Quốc gia Hà Nội 2016
• 主題: Khoa học máy tính; Xử lý ngôn ngữ tự nhiên; Cụm từ; Từ trái nghĩa
• 在線閱讀: http://repository.vnu.edu.vn/handle/VNU_123/8258
• 機構: Vietnam National University, Hanoi

Automatically constructing and clustering of words similarity have many important applications in Natural Language Processing (NLP) tasks, such as dictionary construction, statistical machine translation, named-entity recognition, functional labeling, word segmentation… In recent years, it is a common trend that word clustering is researched in some languages as English, Germany, Chinese… However, the task of word clustering in Vietnamese is a more recent one. In this thesis, I use a large unlabeled data of Vietnamese of about 15 millions words which is equivalent to approximately 700 thousands of sentences. This unlabeled data is extracted from newspapers: Lao dong, PC World, Tuoi tre and then part-of-speech tagged. I investigated some approaches for constructing word clusters in Vietnamese, in which I mainly focus on two main methods by Brown and Dekang Lin. I use the same Vietnamese corpus and the same evaluating tool for these two methods so that I can compare and evaluate the effects of those methods in certain NLP tasks. Besides, I use the statistics method to suggest 20 frames of antonym which can be used to identify antonym classes in clusters.