Edinburgh’s Submission to all Tracks of the WMT 2009 Shared Task with Reordering and Speed Improvements to Moses

By Philipp Koehn, Barry Haddow. 2009

49 citations recorded by the source corpus.

PCT No. PCT/JP90/01270 Sec. 371 Date Apr. 1, 1992 Sec. 102(e) Date Apr. 1, 1992 PCT Filed Oct. 2, 1990 PCT Pub. No. WO91/04751 PCT Pub. Date Apr. 18, 1991.A drug for preventing the absorption of food materials dissolved during digestion, a drug for preventing obesity, a drug for treating hyperlipemia, a drug for treating diabetes mellitus, and a drug for preventing constipation, wherein the flocculant and other auxiliary additives at request, are coated with the aquatic enteric material.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Findings of the 2009 Workshop on Statistical Machine Translation (2009, background): “, 2009) UEDIN University of Edinburgh (Koehn and Haddow, 2009) UKA University of Karlsruhe (Niehues et al.”
The Edinburgh/JHU Phrase-based Machine Translation Systems for WMT 2015 (2015, background): “…(Huang and Chiang, 2007) with a stack size of 5000 (reduced to 1000 for tuning), Minimum Bayes Risk decoding (Kumar and Byrne, 2004), a maximum phrase length of 5, a distortion limit of 6, 100-best translation options and the no-reordering-over-punctuation heuristic (Koehn and Haddow, 2009).”
English SLT and MT system description for the IWSLT 2013 evaluation (2013, background): “• batch k-best MIRA tuning [26] • interpolated 5-gram KenLM language models [27] • minimum Bayes risk decoding [28] • no-reordering-over-punctuation heuristic [29]”
The QT21/HimL Combined Machine Translation System (2016, methodology): “In decoding, we use MBR (Kumar and Byrne, 2004), cube-pruning (Huang and Chiang, 2007) with a pop-limit of 5000, and the Moses ”monotone at punctuation” switch (to prevent reordering across punctuation) (Koehn and Haddow, 2009).”
Edinburgh’s Statistical Machine Translation Systems for WMT16 (2016, background): “…(Huang and Chiang, 2007) with a stack size of 5000 (reduced to 1000 for tuning), Minimum Bayes Risk decoding (Kumar and Byrne, 2004), a maximum phrase length of 5, a distortion limit of 6, 100-best translation options and the no-reordering-over-punctuation heuristic (Koehn and Haddow, 2009).”
A Joint Sequence Translation Model with Integrated Reordering (2011, background): “creasing the Moses stack size from 200 to 1000 does not have a significant effect on translation into English, see (Koehn and Haddow, 2009) and other shared task papers.”
The JHU Machine Translation Systems for WMT 2016 (2016, background): “, 2009), a distortion limit of 6, maximum phrase-length of 5, 100-best translation options, compact phrase table (JunczysDowmunt, 2012) minimum Bayes risk decoding (Kumar and Byrne, 2004), cube pruning (Huang and Chiang, 2007), with a stack-size of 1000 during tuning and 5000 during test and the nor”
A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages (2010, methodology): “Research in translating into morphologically rich languages, has attracted interest for languages like Arabic (Badr et al., 2008), Greek (Avramidis and Koehn, 2008), Hungarian (Novák, 2009; Koehn and Haddow, 2009), Russian (Toutanova et al., 2008), and Turkish (Oflazer and El-Kahlout, 2007).”