TAILIEUCHUNG - Báo cáo khoa học: "A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar"

Recently, various synchronous grammars are proposed for syntax-based machine translation, . synchronous context-free grammar and synchronous tree (sequence) substitution grammar, either purely formal or linguistically motivated. Aiming at combining the strengths of different grammars, we describes a synthetic synchronous grammar (SSG), which tentatively in this paper, integrates a synchronous context-free grammar (SCFG) and a synchronous tree sequence substitution grammar (STSSG) for statistical machine translation. The experimental results on NIST MT05 Chinese-to-English test set show that the SSG based translation system achieves significant improvement over three baseline systems. . | A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar Hongfei Jiang Muyun Yang Tiejun Zhao Sheng Li and Bo Wang School of Computer Science and Technology Harbin Institute of Technology hfjiang ymy tjzhao lisheng bowang @ Abstract Recently various synchronous grammars are proposed for syntax-based machine translation . synchronous context-free grammar and synchronous tree sequence substitution grammar either purely formal or linguistically motivated. Aiming at combining the strengths of different grammars we describes a synthetic synchronous grammar SSG which tentatively in this paper integrates a synchronous context-free grammar SCFG and a synchronous tree sequence substitution grammar STSSG for statistical machine translation. The experimental results on NIST MT05 Chinese-to-English test set show that the SSG based translation system achieves significant improvement over three baseline systems. 1 Introduction The use of various synchronous grammar based formalisms has been a trend for statistical machine translation SMT Wu 1997 Eisner 2003 Galley et al. 2006 Chiang 2007 Zhang et al. 2008 . The grammar formalism determines the intrinsic capacities and computational efficiency of the SMT systems. To evaluate the capacity of a grammar formalism two factors . generative power and expressive power are usually considered Su and Chang 1990 . The generative power refers to the ability to generate the strings of the language and the expressive power to the ability to describe the same language with fewer or no extra ambiguities. For the current synchronous grammars based SMT to some extent the generalization ability of the grammar rules the usability of the rules for the new sentences can be considered as a kind of the generative power of the grammar and the disam- biguition ability to the rule candidates can be considered as an embodiment of expressive power. However the generalization ability and the dis-ambiguition .

• Báo cáo khoa học
• A Statistical Machine Translation Model
• Synthetic Synchronous Grammar
• Hongfei Jiang
• Muyun Yang
• Tiejun Zhao
• Sheng Li and Bo Wang
• báo cáo khoa học
• báo cáo ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• A Discriminative Latent Variable Model
• Statistical Machine Translation
• A Discriminative Latent Variable Model for Statistical Machine Translation
• N gram based Statistical
• Machine Translation versus Syntax Augmented Machine Translation
• comparison and system combination
• scientific reports
• model language
• process natural language
• Perplexity Minimization
• Translation Model Domain Adaptation
• Translation Model Size Reduction
• Hierarchical Phrase based
• ngôn ngữ tự nhiên
• Translation Model Adaptation
• Monolingual Topic Information
• Improving Pronoun Translation
• Liane Guillou
• Adaptation of Statistical Machine Translation Model
• Cross Lingual Information Retrieval
• Service Context
• Fast and Scalable Decoding
• Language Model Look Ahead
• Phrase based Statistical Machine Translation
• On line Language Model Biasing
• Sankaranarayanan Ananthakrishnan
• A non contiguous Tree Sequence Alignment based Model
• Jun Sun
• A Linguistically Annotated
• Reordering Model
• BTG based Statistical Machine Translation
• Maximum Entropy Based Phrase Reordering Model
• Deyi Xiong Qun Liu and Shouxun Lin
• mô hình ngôn ngữ
• A Clustered Global
• Phrase Reordering Model
• Masaaki Nagata Kuniko Saito
• A Hierarchical Phrase Based Model
• David Chiang
• A Localized Prediction Model
• Christoph Tillmann and Tong Zhang
• Using POS Information
• Morphologically Rich Languages
• Efficient Search
• Interactive Statistical
• Machine Translation
• Bilingually Motivated
• Domain Adapted Word Segmentation
• Using Noisy Bilingual Data
• Stephan Vogel
• Toward Statistical Machine Translation
• Parallel Corpora
• Alexandre Klementiev
• Computational Complexity
• Raghavendra Udupa
• Decoding Algorithm
• Ye Yi Wang and Alex Waibel
• Syntactic Phrase Reordering
• English to Arabic