亚运会英语.pptVIP

Student Seminar Student Seminar A Scalable Decoder for Parsing-based Machine Translation with Equivalent Language Model State Maintenance Zhifei Li and Sanjeev Khudanpur Johns Hopkins University JOSHUA: a scalable open-source parsing-based MT decoder Chart-parsing Hypergraph Hypergraph and Trees How to Integrate an m-gram LM? Equivalent State Maintenance: overview Back-off Parameterization of m-gram LMs Equivalent State Maintenance: Right-side Equivalent State Maintenance: Left-side Equivalent State Maintenance: summary Experimental Results: Decoding Speed Experimental Results: Distributed LM Experimental Results: Equivalent LM States Summary Acknowledgements Grammar Formalism Chart-parsing m-gram LM Integration Parallel and Distributed Decoding Chart-parsing Hypergraph * Written in JAVA language Chart-parsing Beam and Cube pruning K-best extraction over a hypergraph m-gram LM Integration Parallel Decoding Distributed LM (Zhang et al., 2006; Brants et al., 2007) Equivalent LM state maintenance We plan to add more functions soon New! Chiang (2007) Grammar formalism Synchronous Context-free Grammar (SCFG) Chart parsing Bottom-up parsing It maintains a chart, which contains an array of cells or bins A cell maintains a list of items The parsing process starts from axioms, and proceeds by applying the inference rules to prove more and more items, until a goal item is proved. The hypotheses are stored in a hypergraph. item hyperedge on the mat a cat X | 3, 4 | a cat | NA X | 0, 2 | the mat | NA X | 0, 4 | a cat | the mat X (猫, a cat) X | 0, 4 | the mat | a cat X (X0 的 X1, X0 X1) X (X0 的 X1, X0 ’s X1) (X0, X0) S Goal Item (X0, X0) S X (垫子 上, the mat) X (X0 的 X1, X1 of X0) X (X0 的 X1, X1 on X0) 猫3 垫子0 上1 的2 of 猫3 垫子0 上1 的2 X (猫, a cat) X (垫子 上, the mat) X (X0 的 X1, X0 X1) (X0, X0) S the mat a cat X (猫, a cat) 猫3 垫子0 上1 的2 X (垫子 上, the mat) (X0, X0) S X (X0 的 X1, X0 ’s X1) the mat ’s a cat X (猫, a cat) 猫3 a cat