Factored Translation Models

By Philipp Koehn, Hieu D. Hoang. 2007

661 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): “The inclusion of such an additional factor is trivial given the factored model implementation (Koehn and Hoang, 2007) of Moses (Koehn et al.”
Findings of the 2016 Conference on Machine Translation (2016, methodology): “By enabling a straightforward integration of additional annotation (factors) at the word-level, factored translation models (Koehn and Hoang, 2007) are used to leverage such complementarity.”
What do Neural Machine Translation Models Learn about Morphology? (2017, background): “…systems that deal with morphologically-rich languages resort to various techniques for representing morphological knowledge, such as word segmentation (Nieﬂen and Ney, 2000 Knight, 2003; Badr et al., 2008) and factored translation and reordering models (Koehn and Hoang, 2007; Durrani et al., 2014).”
Moses: Open Source Toolkit for Statistical Machine Translation (2007, background): “Initial results show the potential benefit of factors for statistical machine translation, (Koehn et al. 2006) and (Koehn and Hoang 2007).”
How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs (2016, background): “…interesting phenomena that have previously been found to be challenging for machine translation, including agreement over long distances (Koehn and Hoang, 2007; Williams and Koehn, 2011), discontiguous verb-particle constructions (Nießen and Ney, 2000; Loáiciga and Gulordava, 2016),…”
Minimum Risk Training for Neural Machine Translation (2015, methodology): “We ﬁnd that introducing minimum risk training into neural MT leads to surprisingly substantial improvements over M OSES and RNN SEARCH with MLE as the training criterion (up to +8.61 and +7.20 BLEU points, respectively) across all test sets.”
(Meta-) Evaluation of Machine Translation (2007, methodology): “…training corpora • development and dev-test sets • language models trained for each language • an open source decoder for phrase-based SMT called Moses (Koehn et al., 2006), which re-places the Pharaoh decoder (Koehn, 2004) • a training script to build models for Moses The performance of this…”
EU-BRIDGE MT: Combined Machine Translation (2014, methodology): “UEDIN uses POS and morphological target sequence models built on the in-domain subset of the parallel corpus using Kneser-Ney smoothed 7-gram models as additional factors in phrase translation models (Koehn and Hoang, 2007).”
Unsupervised Morphology Rivals Supervised Morphology for Arabic MT (2012, background): “For instance, factored translation Models (Koehn and Hoang, 2007; Yang and Kirchhoff, 2006; Avramidis and Koehn, 2008) parametrize translation probabilities as factors encoding morphological features.”
Neural Machine Translation: A Review (2019, methodology): “This technique is popular for traditional statistical machine translation [181, 590], and has been applied to neural machine translation both on the input [591] and the output [592, 593] side.”
The DCU-ICTCAS MT system at WMT 2014 on German-English Translation Task (2014, methodology): “In our system, we adopt three Lexicalized Reordering Models (LRMs) for addressing this problem.”
Applying Morphology Generation Models to Machine Translation (2008, methodology): “In recent work, Koehn and Hoang (2007) proposed a general framework for including morphological features in a phrase-based SMT system by factoring the representation of words into a vector of morphological features and allowing a phrase-based MT system to work on any of the factored…”
The UA-Prompsit hybrid machine translation system for the 2014 Workshop on Statistical Machine Translation (2014, methodology): “We built a baseline PBSMT Moses (Koehn et al., 2007) system 6 from a subset of the parallel corpora distributed as part of the WMT 2014 shared translation task, namely Europarl (Koehn, 2005), News Commentary and Common Crawl, and a subset of the French monolingual corpora, namely Common Crawl, Europ”
The AFRL-MITLL WMT15 System: There’s More than One Way to Decode It! (2015, methodology): “For our last system, we used a factored phrasebased approach (Koehn and Hoang, 2007) where the surface form of the training data was augmented with word classes.”
Edinburgh’s Submission to all Tracks of the WMT 2009 Shared Task with Reordering and Speed Improvements to Moses (2009, methodology): “part-of-speech language model — We use factored translation models (Koehn and Hoang, 2007) to also output part-of-speech tags with each word in a single phrase mapping and run a second n-gram model over them.”
WordICA—emergence of linguistic representations for words by independent component analysis (2010, methodology): “POS tagging has been investigated in relation to statistical machine translation in which the factor models can be enriched with the tags (Ueﬃng and Ney 2003; Koehn and Hoang 2007).”
A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages (2010, methodology): “While the factored translation model (Koehn and Hoang, 2007) in Moses does allow scoring with models of different granularity, e.”
The Operation Sequence Model—Combining N-Gram-Based and Phrase-Based Statistical Machine Translation (2015, positive): “Our Moses (Koehn et al. 2007) baseline systems are based on the setup described in Durrani et al.”
Variational Neural Machine Translation (2016, methodology): “Speciﬁcally, when d z = 4000 , VNMTx obtains the best average results that gain 0.71 and 1.20 BLEU points over Moses and GroundHog respectively.”