Model With Minimal Translation Units, But Decode With Phrases

By Nadir Durrani, Alexander M. Fraser, Helmut Schmid. 2013

42 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): “We trained our systems with the following settings: a maximum sentence length of 80, growdiag-final-and symmetrization of GIZA++ alignments, an interpolated Kneser-Ney smoothed 5- gram language model with KenLM (Heafield, 2011) used at runtime, hierarchical lexicalized reordering (Galley and Manning”
EU-BRIDGE MT: Combined Machine Translation (2014, methodology): “UEDIN’s phrase-based systems (Durrani et al., 2014) have been trained using the Moses toolkit (Koehn et al., 2007), replicating the settings described in (Durrani et al., 2013b).”
Can Markov Models Over Minimal Translation Units Help Phrase-Based SMT? (2013, background): “Durrani et al. (2013) showed that using larger phrasal units during decoding is superior to MTU-based decoding in an N-gram-based system.”
Edinburgh SLT and MT system description for the IWSLT 2014 evaluation (2014, methodology): “We investigated applying a number of OSM models [32, 33] to the basic phrase-based translation model.”
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 Machine Translation Systems for European Language Pairs (2013, methodology): “Please refer to (Durrani et al., 2013b) for details.”
English SLT and MT system description for the IWSLT 2013 evaluation (2013, methodology): “The integration of the OSM model into phrase-based decoding [40, 41] addresses the problem of phrasal independence assumption since the model considers context beyond phrasal boundaries.”
The Operation Sequence Model—Combining N-Gram-Based and Phrase-Based Statistical Machine Translation (2015, unknown): “The future cost estimates computed in this manner are much more accurate because not only do they consider context, but they also take the reordering operations into account (Durrani, Fraser, and Schmid 2013).”