Clause Restructuring for Statistical Machine Translation

By Michael Collins, Philipp Koehn, Ivona Kucerova. 2005

665 citations recorded by the source corpus.

We describe a method for incorporating syntactic information in statistical machine translation systems. The first step of the method is to parse the source language string that is being translated. The second step is to apply a series of transformations to the parse tree, effectively reordering the surface string on the source language side of the translation system. The goal of this step is to recover an underlying word order that is closer to the target language word-order than the original string. The reordering approach is applied as a pre-processing step in both the training and decoding phases of a phrase-based statistical MT system. We describe experiments on translation from German to English, showing an improvement from 25.2% Bleu score for a baseline system to 26.8% Bleu score for the system with reordering, a statistically significant improvement.

Subfields: Artificial Intelligence, 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 Natural Language Processing

Citations in the corpus

Edinburgh’s Phrase-based Machine Translation Systems for WMT-14 (2014, methodology): “We used syntactic-preordering (Collins et al., 2005) and compound splitting (Koehn and Knight, 2003) for German-to-English systems.”
Modeling Coverage for Neural Machine Translation (2016, methodology): “We use sign-test (Collins et al., 2005) for statistical significance test.”
Manual and Automatic Evaluation of Machine Translation between European Languages (2006, methodology): “The bootstrap method has been critized by Riezler and Maxwell (2005) and Collins et al. (2005), as being too optimistic in deciding for statistical significant difference between systems.”
EU-BRIDGE MT: Combined Machine Translation (2014, methodology): “UEDIN has applied syntactic prereordering (Collins et al., 2005) and compound splitting (Koehn and Knight, 2003) of the source side for the German→English system.”
Encoding Source Language with Convolutional Neural Network for Machine Translation (2015, methodology): “Metric: We use the case-insensitive 4-gram NIST BLEU3 as our evaluation metric, with statistical significance test with sign-test (Collins et al., 2005) between the proposed models and two baselines.”
BEER: BEtter Evaluation as Ranking (2014, methodology): “3. facilitates easier statistical testing using sign test or t-test (Collins et al., 2005) We think that the root cause for most of the difﬁ-culty in creating a good sentence level metric is the sparseness of the features often used.”
The Hitchhiker’s Guide to Testing Statistical Significance in Natural Language Processing (2018, background): “Yet, it has been used in a variety of NLP papers (e.g. (Collins et al., 2005; Chan et al., 2007; Rush et al., 2012)).”
The Edinburgh/JHU Phrase-based Machine Translation Systems for WMT 2015 (2015, methodology): “For translation from German, we applied syntactic pre-reordering (Collins et al., 2005) and compound splitting (Koehn and Knight, 2003) in a preprocessing step on the source side.”
Neural Machine Translation with Reconstruction (2016, neutral): “2002) as evaluation metric, and signtest (Collins et al. 2005) for statistical significance test.”
Syntax-based Rewriting for Simultaneous Machine Translation (2015, background): “This work is also related to preprocessing re-ordering approaches (Xu et al., 2009; Collins et al., 2005; Galley and Manning, 2008; Hoshino et al., 2013; Hoshino et al., 2014) in batch MT for language pairs with substantially different word orders.”
Edinburgh’s Machine Translation Systems for European Language Pairs (2013, methodology): “…large tuning set consisting of the test sets from 2008-2010, with a total of 7,567 sentences per language • German–English with syntactic pre-reordering (Collins et al., 2005), compound splitting (Koehn and Knight, 2003) and use of factored representation for a POS target sequence model (Koehn…”
Factored Translation Models (2007, background): “Structural problems have also been addressed by pre-processing: Collins et al. (2005) reorder the input to a statistical system to closer match the word order of the output language.”
Syntactic Phrase Reordering for English-to-Arabic Statistical Machine Translation (2009, background): “It describes the rich morphology of Arabic, and its implications on SMT.”
Experiments in Morphosyntactic Processing for Translating to and from German (2009, methodology): “…we allowed: e , en , n , es , s , em and er , which is more aggressive Table 3: Differences in reordering: BEFORE is re-ordering using rules in (Collins et al., 2005), AF-TER is our modiﬁed reordering than used in previous work (and therefore generalizes more but at the same time causes some…”
Word Sense Disambiguation Improves Statistical Machine Translation (2007, methodology): “…in (Chiang, 2005), perhaps due to differences in word segmentation, etc. Note that comparing with the MT systems used in (Carpuat and Wu, 2005) and (Cabezas and Resnik, 2005), the Hiero system we are using represents a much stronger baseline MT system upon which the WSD system must improve.”
Enriching Parallel Corpora for Statistical Machine Translation with Semantic Negation Rephrasing (2012, background): “Collins et al. (2005) approach the problem of properly translating negation in their general reordering setting.”
Edinburgh’s Statistical Machine Translation Systems for WMT16 (2016, methodology): “For phrase-based translation from German, we applied syntactic pre-reordering (Collins et al., 2005) and compound splitting (Koehn and Knight, 2003) in a preprocessing step on the source side.”