TAILIEUCHUNG - Báo cáo khoa học: "Name Translation in Statistical Machine Translation Learning When to Transliterate"

We present a method to transliterate names in the framework of end-to-end statistical machine translation. The system is trained to learn when to transliterate. For Arabic to English MT, we developed and trained a transliterator on a bitext of 7 million sentences and Google’s English terabyte ngrams and achieved better name translation accuracy than 3 out of 4 professional translators. The paper also includes a discussion of challenges in name translation evaluation. | Name Translation in Statistical Machine Translation Learning When to Transliterate UlfHermjakob and Kevin Knight University of Southern California Information Sciences Institute 4676 Admiralty Way Marina del Rey CA 90292 USA ulf knight @ Hal Daume III University of Utah School of Computing 50 S Central Campus Drive Salt Lake City UT 84112 USA me@ Abstract We present a method to transliterate names in the framework of end-to-end statistical machine translation. The system is trained to learn when to transliterate. For Arabic to English MT we developed and trained a transliterator on a bitext of 7 million sentences and Google s English terabyte ng t am s and achieved better name translation accuracy than 3 out of 4 professional translators. The paper also includes a discussion of challenges in name translation evaluation. 1 Introduction State-of-the-art statistical machine translation SMT is bad at translating names that are not very common particularly across languages with different character sets and sound systems. For example consider the following automatic translation 1 Arabic input SMT output musicians such as Bach l ijjjSyfyyy Correct translation composers such as Bach Mozart Chopin Beethoven Schumann Rachmaninoff Ravel and Prokofiev The SMT system drops most names in this example. Name dropping and mis-translation happens when the system encounters an unknown word mistakes a name for a common noun or trains on noisy parallel data. The state-of-the-art is poor for Taken from NIST02-05 corpora two reasons. First although names are important to human readers automatic MT scoring metrics such as Bleu do not encourage researchers to improve name translation in the context of MT. Names are vastly outnumbered by prepositions articles adjectives common nouns etc. Second name translation is a hard problem even professional human translators have trouble with names. Here are four reference translations taken from the same corpus with mistakes .

• Báo cáo khoa học
• Name Translation
• Statistical Machine Translation
• Learning When to Transliterate
• báo cáo khoa học
• báo cáo ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• A Chinese English Organization Name Translation System
• Heuristic Web Mining
• Asymmetric Alignment
• Combining Source and Target Language Information
• Name Tagging
• Machine Translation Output
• Assessing culture specific references
• A case of Harry Potter’s journey
• Special name in literature
• Evaluation of translation quality
• Literary translation
• 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 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