Dependency Treelet Translation: Syntactically Informed Phrasal SMT

By Chris Quirk, Arul Menezes, Colin Cherry. Annual Meeting of the Association for Computational Linguistics, 2005

441 citations recorded by the source corpus.

We describe a novel approach to statistical machine translation that combines syntactic information in the source language with recent advances in phrasal translation. This method requires a source-language dependency parser, target language word segmentation and an unsupervised word alignment component. We align a parallel corpus, project the source dependency parse onto the target sentence, extract dependency treelet translation pairs, and train a tree-based ordering model. We describe an efficient decoder and show that using these tree-based models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/d9f2186e2e3aab0e697532aeec0d1b88a61af02d

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

Citations in the corpus

What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA (2007, background): “…developed powerful grammatical formalisms and statistical models for representing and learning these tree-to-tree relations (Wu and Wong, 1998; Eisner, 2003; Gildea, 2003; Melamed, 2004; Ding and Palmer, 2005; Quirk et al., 2005; Galley et al., 2006; Smith and Eisner, 2006, inter alia ).”
First- and Second-Order Expectation Semirings with Applications to Minimum-Risk Training on Translation Forests (2009, background): “…to represent the hypothesis space considered (for a given input) by a mono-lingual parser or a tree-based translation system, e.g., tree to string (Quirk et al., 2005; Liu et al., 2006), string to tree (Galley et al., 2006), tree to tree (Eisner, 2003), or string to string with latent tree…”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, background): “String-to-tree approaches map a source sentence to a target tree, and have proved to be quite successful [53, 114, 115, 305, 347, 348]; tree-to-string approaches map a source tree to a target sentence [150, 213, 216, 256, 257, 280]; and tree-to-tree map from a source tree to a target tree [91, 100, ”
Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation (2015, background): “(Chelba et al., 1997; Quirk et al., 2004; Shen et al., 2010; Zhang, 2009; Popel and Marecek, 2010)), there are vast differences in modelling assumptions.”
Posterior Regularization for Structured Latent Variable Models (2010, background): “They are useful for language modeling, textual entailment and machine translation (Haghighi et al., 2005; Chelba et al., 1997; Quirk et al., 2005; Shen et al., 2008), to name a few tasks.”
Quasi-Synchronous Grammars: Alignment by Soft Projection of Syntactic Dependencies (2006, background): “…grammar formalisms more sophisticated than CFG:2 one can permit unaligned nodes (Yamada and Knight, 2001), duplicated children (Gildea, 2003)3, or alignment between elementary trees of differing sizes rather than between single rules (Eisner, 2003; Ding and Palmer, 2005; Quirk et al., 2005).”
Pivot language approach for phrase-based statistical machine translation (2007, methodology): “2003; Och and Ney 2004) and syntax-based methods (Wu 1997; Alshawi et al. 2000; Yamada and Knight 2001; Melamed 2004; Chiang 2005; Quirk et al. 2005; Mellebeek et al. 2006) outperform word-based methods (Brown et al.”
Statistical machine translation (2010, neutral): “Quirk et al. (2005) use a probabilistic model to interleave old dependents and newly adjoint dependents but do not seem allow non-projective attachments.”
The impact of parse quality on syntactically-informed statistical machine translation (2006, methodology): “For syntactically-informed translation, we follow the treelet translation approach described in (Quirk et al., 2005).”
Applying Morphology Generation Models to Machine Translation (2008, methodology): “For the phrase-based system, we generated the annotations needed by first parsing the source sentence e, aligning the source and candidate translations with the word-alignment model used in training, and projected the dependency tree to the target using the algorithm of (Quirk et al., 2005).”
Tree-to-String Alignment Template for Statistical Machine Translation (2006, methodology): “Paying more attention to source language analysis, Quirk et al. (2005) employ a source language dependency parser, a target language word segmentation component, and an unsupervised word alignment component to learn treelet translations from parallel corpus.”