TAILIEUCHUNG - Báo cáo khoa học: "Learning to Transform and Select Elementary Trees for Improved Syntax-based Machine Translations"

We propose a novel technique of learning how to transform the source parse trees to improve the translation qualities of syntax-based translation models using synchronous context-free grammars. We transform the source tree phrasal structure into a set of simpler structures, expose such decisions to the decoding process, and find the least expensive transformation operation to better model word reordering. | Learning to Transform and Select Elementary Trees for Improved Syntax-based Machine Translations Bing Zhao and Young-Suk Lee and Xiaoqiang Luo and Liu Li IBM . Watson Research and Carnegie Mellon University zhaob ysuklee xiaoluo @ and liul@ Abstract We propose a novel technique of learning how to transform the source parse trees to improve the translation qualities of syntax-based translation models using synchronous context-free grammars. We transform the source tree phrasal structure into a set of simpler structures expose such decisions to the decoding process and find the least expensive transformation operation to better model word reordering. In particular we integrate synchronous binarizations verb regrouping removal of redundant parse nodes and incorporate a few important features such as translation boundaries. We learn the structural preferences from the data in a generative framework. The syntax-based translation system integrating the proposed techniques outperforms the best Arabic-English unconstrained system in NIST-08 evaluations by absolute BLEU which is statistically significant. 1 Introduction Most syntax-based machine translation models with synchronous context free grammar SCFG have been relying on the off-the-shelf monolingual parse structures to learn the translation equivalences for string-to-tree tree-to-string or tree-to-tree grammars. However state-of-the-art monolingual parsers are not necessarily well suited for machine translation in terms of both labels and chunks brackets. For instance in Arabic-to-English translation we find only of Arabic NP-SBJ structures are mapped to the English NP-SBJ with machine alignment and parse trees and only of NP-SBJs are mapped with human alignment and parse trees as in 2. The chunking is of more concern at best only source chunking decisions are translated contiguously on the target side. To translate the rest of the chunks one has to frequently break the .

• Báo cáo khoa học
• Learning to Transform
• Select Elementary Trees
• Improved Syntax based Machine Translations
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Detection of cervical cancer
• Learning vector quantization and wavelet transform
• Learning vector quantization
• Train the LVQ
• Human papilloma virus
• Empowering learners
• Triad model to promote eHealth literacy
• Promote eHealth literacy
• Transform learning
• Point of care
• BMC Bioinformatics
• Convolutional neural network
• Stationary wavelet transform
• Cancer prognosis prediction
• RNA sequencing
• Cox regression
• Digital systems supporting cognition
• Exploratory learning
• The educational practitioners
• Large scale take up
• resources available
• stability is present
• transform
• quality between
• section examines
• important small
• Journal of Automation and Control Engineering
• Identifying tuberculosis through exhaled breath
• Field programmable gate array myRIO
• The space of the array
• Fast fourier transform
• BMC Genomics
• Taxonomic classification
• Whole genome analysis
• Genomic signature
• Alignment free sequence analysis
• Machine learning
• Numerical representation of DNA sequences
• Digital signal processing
• Discrete Fourier transform
• Bài giảng Xử lý ngôn ngữ tự nhiên
• Xử lý ngôn ngữ tự nhiên
• Kỹ thuật lập trình
• Mô hình ngôn ngữ
• Mô hình n gram
• Dịch máy
• Phương pháp dịch máy
• Hiểu ngôn ngữ
• Phân loại tin tự động
• Tạo chí tin học
• Điều khiển học
• Truy vấn ngôn ngữ tự nhiên
• Phép dịch truy vấn ngôn ngữ tự nhiên
• Truy vấn SQL
• Văn phạm ngữ nghĩa
• Xử lý nhập nhằng ngữ nghĩa
• Xử lý ngữ nghĩa
• Phân tích ngữ nghĩa
• Biểu diễn vị từ
• Thuộc tính về sự kiện
• Thuộc tính về sự kiện
• Xử lý ngôn ngữ
• Natural Language Processing
• Ngôn ngữ lập trình
• Nhập nhằng cấu trúc
• Tri thức về ngôn ngữ
• Mô hình ngôn ngữ Google Book N grams
• Mô hình ngôn ngữ KenLM
• Phương pháp làm mịn
• Bài toán PTCP
• Phân tích cú pháp
• 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
• Gán nhãn từ loại
• Ngôn ngữ tự nhiên trong dịch máy
• Hệ thống dịch máy
• Phương pháp xây dựng bảng từ
• Tác từ
• Conditional random fields
• Nhận dạng thực thể có tên
• Đối tượng vật lý trừu tượng
• Phân lớp văn bản
• Biểu diễn nhị phân
• Ma trận từ văn bản
• Wolfram Alpha
• Trích rút thông tin
• Phương pháp Snowball