TAILIEUCHUNG - Báo cáo khoa học: "Trimming CFG Parse Trees for Sentence Compression Using Machine Learning Approaches"

Sentence compression is a task of creating a short grammatical sentence by removing extraneous words or phrases from an original sentence while preserving its meaning. Existing methods learn statistics on trimming context-free grammar (CFG) rules. However, these methods sometimes eliminate the original meaning by incorrectly removing important parts of sentences, because trimming probabilities only depend on parents’ and daughters’ non-terminals in applied CFG rules. We apply a maximum entropy model to the above method. . | Trimming CFG Parse Trees for Sentence Compression Using Machine Learning Approaches Yuya Unno1 Takashi Ninomiya2 Yusuke Miyao1 Jun ichi Tsujii134 department of Computer Science University of Tokyo information Technology Center University of Tokyo 3School of Informatics University of Manchester 4SORST JST Hongo 7-3-1 Bunkyo-ku Tokyo Japan unno yusuke tsujii @ ninomi@ Abstract Sentence compression is a task of creating a short grammatical sentence by removing extraneous words or phrases from an original sentence while preserving its meaning. Existing methods learn statistics on trimming context-free grammar CFG rules. However these methods sometimes eliminate the original meaning by incorrectly removing important parts of sentences because trimming probabilities only depend on parents and daughters non-terminals in applied CFG rules. We apply a maximum entropy model to the above method. Our method can easily include various features for example other parts of a parse tree or words the sentences contain. We evaluated the method using manually compressed sentences and human judgments. We found that our method produced more grammatical and informative compressed sentences than other methods. 1 Introduction In most automatic summarization approaches text is summarized by extracting sentences from a given document without modifying the sentences themselves. Although these methods have been significantly improved to extract good sentences as summaries they are not intended to shorten sentences . the output often has redundant words or phrases. These methods cannot be used to make a shorter sentence from an input sentence or for other applications such as generating headline news Dorr et al. 2003 or messages for the small screens of mobile devices. We need to compress sentences to obtain short and useful summaries. This task is called sentence compression. While several methods have been proposed for sentence compression Witbrock .

• Báo cáo khoa học
• Trimming CFG Parse Trees
• Sentence Compression
• Machine Learning Approaches
• 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