Titlebook: Linguistically Motivated Statistical Machine Translation; Models and Algorithm Deyi Xiong,Min Zhang Book 2015 Springer Science+Business Med

fungus

书目名称Linguistically Motivated Statistical Machine Translation影响因子(影响力)




书目名称Linguistically Motivated Statistical Machine Translation影响因子(影响力)学科排名




书目名称Linguistically Motivated Statistical Machine Translation网络公开度




书目名称Linguistically Motivated Statistical Machine Translation网络公开度学科排名




书目名称Linguistically Motivated Statistical Machine Translation被引频次




书目名称Linguistically Motivated Statistical Machine Translation被引频次学科排名




书目名称Linguistically Motivated Statistical Machine Translation年度引用




书目名称Linguistically Motivated Statistical Machine Translation年度引用学科排名




书目名称Linguistically Motivated Statistical Machine Translation读者反馈




书目名称Linguistically Motivated Statistical Machine Translation读者反馈学科排名

好开玩笑

Deyi Xiong,Min Zhang35. The main objective of the paper was to establish the essential (abstract) properties of the concepts of linear dependence and independence in vector spaces, and to use these for the axiomatic definition of a new algebraic object, namely the matroid. Furthermore, Whitney showed that these axioms

做方舟

Deyi Xiong,Min Zhang35. The main objective of the paper was to establish the essential (abstract) properties of the concepts of linear dependence and independence in vector spaces, and to use these for the axiomatic definition of a new algebraic object, namely the matroid. Furthermore, Whitney showed that these axioms

萤火虫

BTG-Based SMT,the model and decoding algorithm that does not integrate language model. We then present an algorithm to integrate standard .-gram language models into the decoder. Following that, we describe two extensions to these traditional language models: a backward language model that augments the convention

军械库

Syntactically Annotated Reordering,sophy behind the model is that reordering under the ITG constraint is considered as a binary classification problem. We therefore build a maximum entropy classification model to predict the order . {.} whenever we apply a BTG bracketing rule to merge two neighboring phrases. As syntax knowledge can

scrutiny

巨硕

擦试不掉

Linguistically Motivated Bracketing,ntroduce a . approach in this chapter that directly determines whether a source segment can be bracketed and translated as a unit or not. We achieve this by using high-level information: syntactic and semantic structure knowledge. In the syntax-driven bracketing model, we employ syntactic knowledge

grieve

Translation Rule Selection with Document-Level Semantic Information,slation rule selection is a task of selecting appropriate translation rules for an ambiguous source-language segment. We represent the gist of a document as the topic of the document. Therefore we introduce two topic-based models for translation rule selection which incorporates global topic informa

helper-T-cells

Translation Error Detection with Linguistic Features,chine translation quality. The previous work is largely based on confidence estimation using system-based features, such as word posterior probabilities calculated from .-best lists or word lattices. We propose to incorporate two groups of linguistic features, which convey information from outside m