tailieunhanh - Báo cáo khoa học: "CL Research’s Knowledge Management System"

CL Research began experimenting with massive XML tagging of texts to answer questions in TREC 2002. In DUC 2003, the experiments were extended into text summarization. Based on these experiments, The Knowledge Management System (KMS) was developed to combine these two capabilities and to serve as a unified basis for other types of document exploration. KMS has been extended to include web question answering, both general and topic-based summarization, information extraction, and document exploration. . | CL Research s Knowledge Management System Kenneth C. Litkowski CL Research 9208 Gue Road Damascus MD 20872 ken@ http Abstract CL Research began experimenting with massive XML tagging of texts to answer questions in TREC 2002. In DUC 2003 the experiments were extended into text summarization. Based on these experiments The Knowledge Management System KMS was developed to combine these two capabilities and to serve as a unified basis for other types of document exploration. KMS has been extended to include web question answering both general and topic-based summarization information extraction and document exploration. The document exploration functionality includes identification of semantically similar concepts and dynamic ontology creation. As development ofKMS has continued user modeling has become a key research issue how will different users want to use the information they identify. 1 Introduction In participating the TREC question-answering track CL Research began by parsing full documents and developing databases consisting of semantic relation triples Litkowski 1999 . The database approach proved to be quite confining with time requirements expanding exponentially trying to maintain larger sets of documents and increasingly complex procedures to answer questions. A suggestion was made to tag text with the type of questions they could answer . tagging time phrases as answering when questions and person names as answering who questions . This led to the general approach of analyzing pars e trees to construct an XML representation of texts . attaching metadata to the text and examining these representations with XPath expressions to answer questions. Litkowski 2003a demonstrated the viability of this approach by showing that XPath expressions could be used to answer questions at a level above the highest performing team. Many issues and problems were identified 1 The necessary level of analysis to meet the needs of particular .

• Báo cáo khoa học
• CL Research’s Knowledge
• Management System
• Kenneth C
• Litkowski
• 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