Can Markov Models Over Minimal Translation Units Help Phrase-Based SMT?

By Nadir Durrani, Alexander M. Fraser, Helmut Schmid, Hieu D. Hoang, Philipp Koehn. 2013

78 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): “Our baseline systems are based on the setup described in (Durrani et al., 2013b) that we used for the Eighth Workshop on Statistical Machine Translation (Bojar et al., 2013).”
The United Nations Parallel Corpus v1.0 (2016, methodology): “Apart from the default conﬁguration with a lexical reordering model, we add a 5-gram operation sequence model (Durrani et al., 2013) (all n-grams pruned if they occur only once) and a 9-gram word-class language model with word-classes produced by word2vec (Mikolov et al., 2013) (3-grams and 4-grams…”
The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT (2016, background): “Although SMT seems to be better equipped to handle large vo-cabularies, the case of Russian still poses problems which are usually solved with transliteration mechanisms (Durrani et al., 2014).”
On the Impact of Various Types of Noise on Neural Machine Translation (2018, background): “…KenLM (Heaﬁeld, 2011), hierarchical lexicalized reordering (Galley and Manning, 2008), a lexically-driven 5-gram operation sequence model (OSM) (Durrani et al., 2013), sparse domain indicator, phrase length, and count bin features (Blunsom and Osborne, 2008; Chiang et al., 2009), a maximum…”
The Edinburgh/JHU Phrase-based Machine Translation Systems for WMT 2015 (2015, methodology): “We used all four factors (words and clusters) in both source and target languages for the the translation model and the OSM, but we used only the word factor for the alignment and the reordering models.”
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…”
A Comprehensive Survey of Grammar Error Correction (2020, methodology): “Sequence Model is introduced into Moses for machine translation [41].”
Improving machine translation via triangulation and transliteration (2014, unknown): “6 Hindi-English: For Hindi-English systems, we additionally used hierarchical lexicalized reordering (Galley and Manning, 2008), a 5-gram OSM, (Durrani et al., 2013), sparse lexical and domain features, (Hasler et al., 2012), class-based models (Durrani et al., 2014b), a distortion limit of 6, and t”
A Comprehensive Survey of Grammatical Error Correction (2021, methodology): “Operation Sequence Model is introduced into Moses for machine translation [37].”
Investigating the Usefulness of Generalized Word Representations in SMT (2014, methodology): “The integration of the Operation Sequence Model into phrase-based paradigm (Durrani et al., 2013a; Durrani et al., 2013b) improved the reordering capability and addressed the problem of the phrasal independence assumption in the phrase-based models.”
Edinburgh’s Statistical Machine Translation Systems for WMT16 (2016, methodology): “We also used the operation sequence model (OSM) (Durrani et al., 2013) with 4 count based supportive features.”
N-gram Counts and Language Models from the Common Crawl (2014, methodology): “…Kneser-Ney smoothed 5-gram language model with KenLM (Heafield et al., 2013) used at runtime, a lexically-driven 5-gram operation sequence model (Durrani et al., 2013), msd-bidirectional-fe lexicalized reordering, sparse lexical and domain features (Hasler et al., 2012), a distortion limit of…”
Edinburgh’s Machine Translation Systems for European Language Pairs (2013, methodology): “Please refer to (Durrani et al., 2013b) for details.”
The JHU Machine Translation Systems for WMT 2016 (2016, methodology): “We trained our systems with the following settings: a maximum sentence length of 80, grow-diag-ﬁnal-and symmetrization of GIZA++ alignments, an interpolated Kneser-Ney smoothed 5-gram language model with KenLM (Heaﬁeld, 2011) used at runtime, hierarchical lexicalized re-ordering (Galley and Manning,”