Edinburgh’s Statistical Machine Translation Systems for WMT16

By Philip Williams, Rico Sennrich, Maria Nadejde, Matthias Huck, Barry Haddow, Ondrej Bojar. 2016

28 citations recorded by the source corpus.

This paper describes the University of Edinburgh’s phrase-based and syntax-based submissions to the shared translation tasks of the ACL 2016 First Conference on Machine Translation (WMT16). We submitted five phrase-based and five syntaxbased systems for the news task, plus one phrase-based system for the biomedical task.

Subfields: Artificial Intelligence, Molecular Biology, Natural Language Processing

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

In Molecular Biology

In Natural Language Processing

Citations in the corpus

Unsupervised Pretraining for Sequence to Sequence Learning (2016, background): “BLEU System ensemble? newstest2014 newstest2015 Phrase Based MT (Williams et al., 2016) 21.”
Findings of the 2016 Conference on Machine Translation (2016, background): “, 2016) uedin University of Edinburgh, UK (Williams et al., 2016)”
Six Challenges for Neural Machine Translation (2017, methodology): “We build phrasebased systems using standard features that are commonly used in recent system submissions to WMT (Williams et al., 2016; Ding et al., 2016a).”
A Multifaceted Evaluation of Neural versus Phrase-Based Machine Translation for 9 Language Directions (2017, methodology): “Word segmentation is carried out with the help of a lexicon in the EN → FI direction (S´anchez-Cartagena and Toral, 2016) and in an unsupervised way in the remaining directions (Sennrich et al., 2016).”
The Edinburgh/LMU Hierarchical Machine Translation System for WMT 2016 (2016, methodology): “We automatically translated parts (1.2 M sentences) of the mono-lingual Romanian news2015 corpus to English with a Romanian → English phrase-based statistical machine translation system (Williams et al., 2016).”
Neural Machine Translation (2020, unknown): “Further Readings Wu et al. (2012) propose to use factored representations of words (using lemma, stem, and part of speech), with each factor encoded in a one-hot vector, in the input to a recurrent neural network language model.”
Neural Machine Translation Training in a Multi-Domain Scenario (2017, methodology): “A naı̈ve yet commonly used method when training both statistical [14]1 and neural machine translation systems [15] is to simply concatenate all the bilingual parallel data before training the system.”
Linguistic Input Features Improve Neural Machine Translation (2016, methodology): “In addition, we compare our neural systems against phrase-based (PB-SMT) and syntax-based (SBSMT) systems by (Williams et al., 2016), all of which make use of linguistic annotation on the source and/or target side.”