Edinburgh SLT and MT system description for the IWSLT 2014 evaluation

By Alexandra Birch, Matthias Huck, Nadir Durrani, Nikolay Bogoychev, Philipp Koehn. 2014

31 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Edinburgh’s Phrase-based Machine Translation Systems for WMT-14 (2014, methodology): “For the English-to-German sys-tem we added an OSM model over [pos, morph] (source:pos, target:morph) and for the German-to-English system we added an OSM model over [morph,pos] (source:morph, target:pos), a conﬁg-uration that was found to work best in our previous experiments (Birch et al., 2013).”
EU-BRIDGE MT: Combined Machine Translation (2014, background): “over automatically built word classes (Birch et al., 2013).”
The Edinburgh/JHU Phrase-based Machine Translation Systems for WMT 2015 (2015, methodology): “We built upon Edinburgh’s strong baselines from WMT submissions in previous years (Durrani et al., 2014a) as well as our recent research within the framework of other evaluation campaigns and projects such as IWSLT 2 and EU-BRIDGE (Birch et al., 2014; Freitag et al., 2014a; Freitag et al., 2014b).”
Integrating an Unsupervised Transliteration Model into Statistical Machine Translation (2014, methodology): “See Table 1 Baseline Settings: We trained a Moses system replicating the settings used in competition-grade systems (Durrani et al., 2013b; Birch et al., 2013): a maximum sentence length of 80, GDFA sym-metrization of GIZA++ alignments (Och and Ney, 2003), an interpolated Kneser-Ney smoothed 5-gram…”
Report on the 11th IWSLT evaluation campaign (2014, background): “& Thai Nguyen University, Vietnam[17] KIT Karlsruhe Institute of Technology, Germany [18, 19] KLE Pohang University of Science and Technology, Republic of Korea LIA Laboratoire Informatique d’Avignon (LIA) University of Avignon, France [20] LIMSI LIMSI - LIMSI, France [21] LIUM LIUM, University of L”
The Operation Sequence Model—Combining N-Gram-Based and Phrase-Based Statistical Machine Translation (2015, unknown): “16 We also found using morphological tags and automatic word clusters to be useful in our recent IWSLT evaluation campaign (Birch et al. 2013; Durrani et al. 2014).”
N-gram Counts and Language Models from the Common Crawl (2014, background): “Additionally target-side language models over automatically built word-classes (Birch et al., 2013) were built.”
Understanding and Improving Morphological Learning in the Neural Machine Translation Decoder (2017, methodology): “These have been used frequently to annotate data in the previous evaluation campaigns (Birch et al., 2014; Durrani et al., 2014a).”