文档介绍：computer science/machine learning
Learning Machine Trans l a
Cyril Goutte and e Foster are researchers in the Inter- Contributors Learning Machine Translation
active Language Technologies Group at the Canadian Nation- Srinivas Bangalore, Nicola Cancedda, Josep M. Crego, Marc Dymetman, Jakob Elming, e Foster, edited by Cyril Goutte, Nicola Cancedda, Marc Dymetman,
al Research Council’s Institute for Information Technology. Jesús Giménez, Cyril Goutte, Nizar Habash, Gholamreza Haffari, Patrick Haffner, Hitoshi Isahara, Stephan and e Foster
Nicola Cancedda and Marc Dymetman are researchers in the Kanthak, Alexandre Klementiev, Gregor Leusch, Pierre Mahé, Lluís Màrquez, Evgeny Matusov, I. Dan
Cross-Language Technologies Research Group at the Xerox Melamed, Ion Muslea, Hermann Ney, Bruno Pouliquen, Dan Roth, Anoop Sarkar, John Shawe-Taylor,
Research Centre Europe. Ralf Steinberger, Joseph Turian, Nicola Ueffing, Masao Utiyama, Zhuoran Wang, Benjamin Wellington,
Kenji Yamada
Of related interest
Predicting Structured Data
edited by Gökhan Bakır, Thomas Hofmann, Bernhard Schölkopf, Alexander J. Smola, Ben Taskar, and
. Vishwanathan
Machine learning develops puter systems that are able to generalize from previously
seen examples. A new domain of machine learning, in which the prediction must satisfy the additional t ion
constraints found in structured data, poses one of machine learning’s greatest challenges: learning Learning Machine Translation
functional dependencies between arbitrary input and output domains. This volume presents and ana-
lyzes the state of the art in machine learning algorithms and theory in this novel field.
Large-Scale Kernel Machines Goutte, Cancedda, Dymetman, and Foster, editors
edited by Léon Bottou, Olivier Chapelle, Dennis DeCoste, and Jason Weston
Pervasive puters have dramatically reduced the cost of collecting and distributing
large datasets. In this context, machine learning algorithms that sca