TAILIEUCHUNG - Báo cáo khoa học: "The Effect of Corpus Size in Combining Supervised and Unsupervised Training for Disambiguation"

We investigate the effect of corpus size in combining supervised and unsupervised learning for two types of attachment decisions: relative clause attachment and prepositional phrase attachment. The supervised component is Collins’ parser, trained on the Wall Street Journal. The unsupervised component gathers lexical statistics from an unannotated corpus of newswire text. We find that the combined system only improves the performance of the parser for small training sets. Surprisingly, the size of the unannotated corpus has little effect due to the noisiness of the lexical statistics acquired by unsupervised learning. . | The Effect of Corpus Size in Combining Supervised and Unsupervised Training for Disambiguation Michaela Atterer Institute for NLP University of Stuttgart atterer@ Hinrich Schutze Institute for NLP University of Stuttgart hinrich@ Abstract We investigate the effect of corpus size in combining supervised and unsupervised learning for two types of attachment decisions relative clause attachment and prepositional phrase attachment. The supervised component is Collins parser trained on the Wall Street Journal. The unsupervised component gathers lexical statistics from an unannotated corpus of newswire text. We find that the combined system only improves the performance of the parser for small training sets. Surprisingly the size of the unannotated corpus has little effect due to the noisiness of the lexical statistics acquired by unsupervised learning. 1 Introduction The best performing systems for many tasks in natural language processing are based on supervised training on annotated corpora such as the Penn Treebank Marcus et al. 1993 and the prepositional phrase data set first described in Ratnaparkhi et al. 1994 . However the production of training sets is expensive. They are not available for many domains and languages. This motivates research on combining supervised with unsupervised learning since unannotated text is in ample supply for most domains in the major languages of the world. The question arises how much annotated and unannotated data is necessary in combination learning strategies. We investigate this question for two attachment ambiguity problems relative clause RC attachment and prepositional phrase PP attachment. The supervised component is Collins parser Collins 1997 trained on the Wall Street Journal. The unsupervised component gathers lexical statistics from an unannotated corpus of newswire text. The sizes of both types of corpora annotated and unannotated are of interest. We would expect that large annotated .

• Báo cáo khoa học
• The Effect of Corpus Size
• Combining Supervised
• Unsupervised Training for Disambiguation
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Bài giảng Xử lý ngôn ngữ tự nhiên
• Ngôn ngữ tự nhiên
• Kỹ thuật lập trình
• Xử lý nhập nhằng ngữ nghĩa
• Xử lý ngữ nghĩa
• Xử lý ngôn ngữ
• Natural Language Processing
• Ngôn ngữ lập trình
• Nhập nhằng cấu trúc
• Tri thức về ngôn ngữ
• Mô hình n gram
• Dịch máy
• Phương pháp dịch máy
• Hiểu ngôn ngữ
• Phân tích ngữ nghĩa
• Phân loại tin tự động
• Biểu diễn vị từ
• Thuộc tính về sự kiện
• Thuộc tính về sự kiện
• Mô hình ngôn ngữ Google Book N grams
• Mô hình ngôn ngữ KenLM
• Phương pháp làm mịn
• Tách từ tiếng Việt
• Gán nhãn từ loại
• Phân tích cú pháp
• Nghĩa từ vựng
• Phân giải nhập nhằng từ
• Phân loại văn bản
• Lexical chain
• Phản hồi thông tin
• Bài toán PTCP
• Cấu trúc ngữ pháp
• Phân tích cú pháp xác suất
• CKY kết hợp xác suất
• Văn phạm phi ngữ cảnh xác suất
• Hình thái học