Linguistically Motivated Statistical Machine Translation

This book provides a wide variety of algorithms and models to integrate linguistic knowledge into Statistical Machine Translation (SMT). It helps advance conventional SMT to linguistically motivated SMT by enhancing the following three essential components: translation, reordering and bracketing models. It also serves the purpose of promoting the in-depth study of the impacts of linguistic knowledge on machine translation. Finally it provides a systematic introduction of Bracketing Transduction Grammar (BTG) based SMT, one of the state-of-the-art SMT formalisms, as well as a case study of linguistically motivated SMT on a BTG-based platform.

Provides solutions for open problems concerning the integration of linguistic knowledge into SMT Helps readers to better understand the effects and impacts of linguistic knowledge on machine translation Promotes the often-ignored bracketing model (or phrase segmentation model) to the SMT community Elaborates on the entire framework of BTG-based SMT formalism Includes supplementary material: sn.pub/extras

Autorentext

Deyi Xiong is a professor at Soochow University. Previously he was a research scientist at the Institute for Infocomm Research of Singapore from 2007-2013. He completed his Ph.D. in Computer Science at the Institute of Computing Technology of Chinese Academy of Sciences in 2007. His research interests are in the area of natural language processing, including parsing and statistical machine translation.

Min Zhang is a professor at Soochow University. He obtained his Ph.D. degree in Computer Science at Harbin Institute of Technology in 1997. His research interests include machine translation, natural language processing and text mining.

Inhalt
1 Introduction.- 2 BTG-Based SMT.- 3 Syntactically Annotated Reordering.- 4 Semantically Informed Reordering.- 5 Lexicalized Bracketing.- 6 Linguistically Motivated Bracketing.- 7 Translation Rule Selection with Document-Level Semantic Information.- 8 Translation Error Detection with Linguistic Features.- 9 Closing Remarks.- Index.- References.