Learning machine translation


Editors: Cyril Goutte, Nicola Cancedda, Marc Dymetman, George Foster


The MIT Press, Cambridge, Massachusetts; London, England

(Neural Information Processing Series)

[ISBN: 978-0-262-07297-7]


Table of Contents


1.      A statistical machine translation primer

Nicola Cancedda, Marc Dymetman, George Foster, and Cyril Goutte….. pp.1-37


I   Enabling technologies

2.   Mining patents for parallel corpora

                        Masao Utiyama and Hitoshi Isahara….. pp.41-58

3.      Automatic construction of multilingual name dictionaries

a.Bruno Pouliquen and Ralf Steinberger …. pPp.59-78

4.      Named entity transliteration and discovery in multilingual corpora

a.Alexandre Klementiev and Dan Roth … pp. 79-92

5.      Combination of statistical word alignments based on multiple preprocessing schemes

Jakob Elming, Nizar Habash and Josep M. Crego …. pPp.93-110

6.      Linguistically enriched word-sequence kernels for discriminative language modelling

a.Pierre Mahé and Nicola Cancedda …. pPp.111-128


II Machine translation

7.      Toward purely discriminative training for tree-structured translation models

a.Benjamin Wellington, Joseph Turian and I.Dan Melamed … pp.131-149

8.      Reranking for large-scale statistical machine translation

a.Kenji Yamada and Ion Muslea …. pPp.151-168

9.      Kernel-based machine translation

a.Zhuoran Wang and John Shawe-Taylor … pp.169-184

10.  Statistical machine translation through global lexical selection and sentence reconstruction

a.Srinivas Bangalore, Stephan Kanthak and Patrick Haffner … pp.185-203

11.  Discriminative phrase selection for SMT

a.Jesús Giménez and Lluís Màrquez … pp.205-236

12.  Semisupervised learning for machine translation

a.Nicola Ueffing, Gholamreza Haffari and Anoop Sarkar …. pPp.237-256

13.  Learning to combine machine translation systems

Evgeny Matusov, Gregor Leusch and Hermann Ney … pp.257-276