TAILIEUCHUNG - Báo cáo khoa học: "Combining Multiple Resources to Improve SMT-based Paraphrasing Model∗"

This paper proposes a novel method that exploits multiple resources to improve statistical machine translation (SMT) based paraphrasing. In detail, a phrasal paraphrase table and a feature function are derived from each resource, which are then combined in a log-linear SMT model for sentence-level paraphrase generation. Experimental results show that the SMT-based paraphrasing model can be enhanced using multiple resources. The phrase-level and sentence-level precision of the generated paraphrases are above 60% and 55%, respectively. In addition, the contribution of each resource is evaluated, which indicates that all the exploited resources are useful for generating paraphrases of high quality | Combining Multiple Resources to Improve SMT-based Paraphrasing Model Shiqi Zhao1 Cheng Niu2 Ming Zhou2 Ting Liu1 Sheng Li1 1Harbin Institute of Technology Harbin China zhaosq tliu lisheng @ 2Microsoft Research Asia Beijing China chengniu mingzhou @ Abstract This paper proposes a novel method that exploits multiple resources to improve statistical machine translation SMT based paraphrasing. In detail a phrasal paraphrase table and a feature function are derived from each resource which are then combined in a log-linear SMT model for sentence-level paraphrase generation. Experimental results show that the SMT-based paraphrasing model can be enhanced using multiple resources. The phrase-level and sentence-level precision of the generated paraphrases are above 60 and 55 respectively. In addition the contribution of each resource is evaluated which indicates that all the exploited resources are useful for generating paraphrases of high quality. 1 Introduction Paraphrases are alternative ways of conveying the same meaning. Paraphrases are important in many natural language processing NLP applications such as machine translation MT question answering QA information extraction IE multidocument summarization MDS and natural language generation NLG . This paper addresses the problem of sentencelevel paraphrase generation which aims at generating paraphrases for input sentences. An example of sentence-level paraphrases can be seen below S1 The table was set up in the carriage shed. S2 The table was laid under the cart-shed. This research was finished while the first author worked as an intern in Microsoft Research Asia. Paraphrase generation can be viewed as monolingual machine translation Quirk et al. 2004 which typically includes a translation model and a language model. The translation model can be trained using monolingual parallel corpora. However acquiring such corpora is not easy. Hence data sparseness is a key problem for the SMT-based .

• Báo cáo khoa học
• Combining Multiple Resources
• Improve SMT based Paraphrasing Model
• Shiqi Zhao
• báo cáo khoa học
• báo cáo ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Combining Multiple
• Large Scale Resources in a Reusable Lexicon
• Natural Language Generation
• mô hình ngôn ngữ
• 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