非受限训练语料受限训练语料.PPTVIP

Reorder source sentence into target word order based on source syntactic parsing tree Perform monotonic phrase-based decoding for n-best list of reordered source sentence * We can illusrate the re-ordering process by this example. The re-odering model operates bottom-up, trying to find n-best re-odering results for each sub-tree with 2 or 3 children nodes based on a statistical model, until find the n-best reorering result for the entire sentence at the root node. Taking the VP node as example, the reordering model can generate different orders for its children. Each reordered subtree has a probabilty, and the reordering probability is accumulated bottom-up similarly to the accumulation of bottom-up parsing probability. * 微软亚洲研究院汉英翻译系统CWMT2008评测技术报告 张冬冬 李志灏 李沐 周明 微软亚洲研究院 Outline Overview MSRA Submissions System Description Experiments Training Data Toolkits Chinese-English Machine Translation Chinese-English System Combination Conclusion Evaluation Task Participation 参加与否 语种与领域 评测项目 项目代号 ? 汉英新闻领域 机器翻译 ZH-EN-NEWS-TRANS ? 汉英新闻领域 系统融合 ZH-EN-NEWS-COMBI ? 英汉新闻领域 机器翻译 EN-ZH-NEWS-TRANS ? 英汉科技领域 机器翻译 EN-ZH-SCIE-TRANS MSRA Submission Machine translation task Primary submission Unlimited training corpus Combining: SysA + SysB + SysC + SysD Contrast submission Limited training corpus Combining: SysA + SysB + SysC System combination task Limited training corpus Combining: 10 systems SysA Phrase-based model CYK decoding algorithm BTG grammar Features: Similar with (Koehn, 2004) Maximum Entropy reordering model (Zhang et. al 2007, Xiong et. Al, 2006) SysB Syntactic pre-reordering model (Li et. al, 2007) Motivations Isolating reordering model from decoder Making use of syntactic information SysC Hierarchical phase-based model (David Chiang, 2005) Hiero re-implementation Weighted synchronous CFG SysD String-to-dependency MT (Shen et. al, 2008) Integrating target dependent language model Motivations Target dependent structures integrate linguistic knowledge Directly