Third Machine Translation
26-30 January 2009
Contents
Monday 26 January
Adam Lopez: Statistical machine translation.
Adam Lopez: Evaluating translation quality.
Alon Lavie: Stat-XFER: a general framework for search-based syntax-driven MT.
Jonathan Clark & Greg Hannemann: Czech-to-English translation.
Ondřej Bojar: TectoMT for plaintext freaks.
Tuesday 27 January
Barry Haddow: Word-based models and the EM algorithm.
Francis M. Tyers & Kevin Donnelly: apertium-cy: a collaboratively-developed RBMT system for Welsh to English. [published in Prague Bulletin of Mathematical Linguistics 91, 2009] [presentation]
Joăo Graça, Kuzman Ganchev & Ben Taskar: PostCAT – posterior constrained alignment toolkit. [published in Prague Bulletin of Mathematical Linguistics 91, 2009]
Antal van den Bosch & Peter Berck: Memory based machine translation and language modelling. [published in Prague Bulletin of Mathematical Linguistics 91, 2009] [presentation]
Wednesday 28 January
Chris Dyer: Decoding: phrase-based models.
Zhifei Li, Chris Callison-Burch, Sanjeev Khudanpur, & Wren Thornton: Decoding Joshua: open source, parsing-based machine translation. [published in Prague Bulletin of Mathematical Linguistics 91, 2009]
Omar F. Zaidan: Z-MERT: a fully configurable open source tool for minimum error rate training of machine translation systems. [published in Prague Bulletin of Mathematical Linguistics 91, 2009]
Ashish Venugopal & Andreas Zollmann: Grammar based statistical MT on Hadoop: an end-to-end toolkit for large scale PSCFG based MT. [published in Prague Bulletin of Mathematical Linguistics 91, 2009]
Hieu Hoang & Josh Schroeder: Moses installation and training run-through.
Thursday 29 January
Zdeněk Žabokrtský: TectoMT: software framework for developing MT systems (and other NLP applications).
David Mareček: Analysis and alignment of parallel data in TectoMT.
Ondřej Bojar: Bad news, NLP hacking and feature fishing.
Jana Kravalová: TectoMT tutorial.
Yvette Graham & Josef van Genabith: An open source rule induction tool for transfer-based SMT. [published in Prague Bulletin of Mathematical Linguistics 91, 2009]
Ventsislav Zhechev: Unsupervised generation of parallel treebanks through sub-tree alignment. [published in Prague Bulletin of Mathematical Linguistics 91, 2009] [presentation]
Friday 30 January
Philipp Koehn: Discriminative training and factored translation models.
Panel: future of MT Marathon [not available]
Other presentations:
Adam Lopez: Introduction to statistical machine translation.
Hieu Hoang, Barry Haddow, & Abhishek Arun: Using factored models and MERT in Moses. [not available]
Minimum error rate training lab.
Michal Hrusecky, Tomas Caithaml, & Chris Dyer: Feature function overhaul.