The Edinburgh/JHU Phrase-based Machine Translation Systems for WMT 2015
By Barry Haddow, Matthias Huck, Alexandra Birch, Nikolay Bogoychev, Philipp Koehn. 2015
20 citations recorded by the source corpus.
This paper describes the submission of the University of Edinburgh and the Johns Hopkins University for the shared translation task of the EMNLP 2015 Tenth Workshop on Statistical Machine Translation (WMT 2015). We set up phrase-based statistical machine translation systems for all ten language pairs of this year’s evaluation campaign, which are English paired with Czech, Finnish, French, German, and Russian in both translation directions. Novel research directions we investigated include: neural network language models and bilingual neural network language models, a comprehensive use of word classes, and sparse lexicalized reordering features.
Subfields: Artificial Intelligence, Machine Translation
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
- Philipp Koehn
- Rico Sennrich
- Felix Stahlberg
- Barry Haddow
- Ondrej Bojar
- Graham Neubig
- Alexander M. Fraser
- Luke S. Zettlemoyer
In Machine Translation
- Philipp Koehn
- Rico Sennrich
- Barry Haddow
- Matthias Huck
- Huda Khayrallah
- Philip Williams
- Maria Nadejde
- Alexandra Birch
Citations in the corpus
- Neural Machine Translation of Rare Words with Subword Units (2015, methodology): “We generally follow settings by previous work (Bahdanau et al., 2015; Jean et al., 2015).”
- Findings of the 2015 Workshop on Statistical Machine Translation (2015, neutral): “UEDIN-JHU University of Edinburgh / Johns Hopkins University (Haddow et al., 2015)”
- On the Impact of Various Types of Noise on Neural Machine Translation (2018, methodology): “4 We build phrase-based systems using standard features commonly used in recent system submissions to WMT (Haddow et al., 2015; Ding et al., 2016, 2017).”
- The Edinburgh/LMU Hierarchical Machine Translation System for WMT 2016 (2016, background): “for Edinburgh’s phrase-based systems for the German– English language pair (Haddow et al., 2015).”
- The JHU Machine Translation Systems for WMT 2016 (2016, methodology): “We built upon strong baselines of the Edinburgh-JHU joint WMT submissions from the last year (Haddow et al., 2015), the Edinburgh syntax-based system submissions from the last year (Williams et al., 2015) as well as recent research in the field (Vaswani et al., 2013; Devlin et al., 2014).”
- Edinburgh’s Statistical Machine Translation Systems for WMT16 (2016, methodology): “Similar to last year (Haddow et al., 2015), we built an unconstrained system for Finnish → English us-ing data extracted from OPUS (Tiedemann, 2012).”