A Syntax-based Statistical Translation Model

By Kenji Yamada, Kevin Knight. Annual Meeting of the Association for Computational Linguistics, 2001

849 citations recorded by the source corpus.

We present a syntax-based statistical translation model. Our model transforms a source-language parse tree into a target-language string by applying stochastic operations at each node. These operations capture linguistic differences such as word order and case marking. Model parameters are estimated in polynomial time using an EM algorithm. The model produces word alignments that are better than those produced by IBM Model 5.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/11cd7fbc0ea8605ea498ecfc82b3ff6a44c027e9

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

Citations in the corpus

A Systematic Comparison of Various Statistical Alignment Models (2003, background): “The use of models that explicitly deal with the hierarchical structures of natural language is very promising (Wu 1996; Yamada and Knight 2001).”
Sentence Simplification by Monolingual Machine Translation (2012, methodology): “Phrase-Based Machine Translation (PBMT) is a form of SMT where the translation model aims to translate longer sequences of words (“phrases”) in one go, solving part of the word ordering problem along the way that would be left to the target language model in a word-based SMT system.”
Tree-to-Sequence Attentional Neural Machine Translation (2016, background): “In SMT, it is known that incorporating syntactic constituents of the source language into the models improves word alignment (Yamada and Knight, 2001) and translation accuracy (Liu et al., 2006; Neubig and Duh, 2014).”
What’s in a translation rule? (2004, methodology): “5 Conclusion The fundamental assumption underlying much recent work in statistical machine translation (Yamada and Knight, 2001; Eisner, 2003; Gildea, 2003) is that local transformations (primarily child-node re-orderings) of one-level parent-children substructures are an adequate model for parallel”
Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language (2014, methodology): “W ASP (Word-Alignment-based Semantic Parsing) (Wong & Mooney, 2006) uses state-of-the-art statistical machine translation (SMT) techniques (Brown, Cocke, Della Pietra, Della Pietra, Jelinek, Lafferty, Mercer, & Roossin, 1990; Yamada & Knight, 2001; Chiang, 2005) to learn semantic parsers.”
Efficient Inference through Cascades of Weighted Tree Transducers (2010, methodology): “Additionally, we present novel on-the-fly variants of these algorithms, and compare their performance on a syntax machine translation cascade based on (Yamada and Knight, 2001).”
Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder (2017, methodology): “Although syntax has shown its effectiveness in non-neural statistical machine translation (SMT) systems (Yamada and Knight, 2001; Koehn et al., 2003; Liu et al., 2006; Chiang, 2007), most proposed NMT models (a notable exception being that of Eriguchi et al.”
Semantic Parsing with Bayesian Tree Transducers (2012, methodology): “The tree transducer, a formalism from automata theory which has seen interest in machine translation (Yamada and Knight, 2001; Graehl et al., 2008) and has potential applications in many other areas, is well suited to formalizing such tree transformation based models.”
A Hierarchical Phrase-Based Model for Statistical Machine Translation (2005, methodology): “A system like that of Yamada and Knight (2001) is both formally and linguistically syntax-based: formally because it uses synchronous CFG, linguistically because the structures it is deﬁned over are (on the English side) informed by syntactic theory (via the Penn Treebank).”
A Monolingual Tree-based Translation Model for Sentence Simplification (2010, methodology): “Following the work of Yamada and Knight (2001), we train our model by maximizing P (s|c) over the training corpus with the EM algorithm described in Alg.”
Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features (2014, methodology): “In this article, we present a tree-to-tree machine translation system inspired by quasi-synchronous grammar.”
Learning for Semantic Parsing with Statistical Machine Translation (2006, methodology): “…target MRL. Complete MRs are then formed by combining these NL substrings and their translations under a parsing framework called the synchronous CFG (Aho and Ullman, 1972), which forms the basis of most existing statistical syntax-based translation models (Yamada and Knight, 2001; Chiang, 2005).”
Hierarchical Phrase-Based Translation (2007, neutral): “…of as an example of syntax-based statistical machine translation (MT), joining a line of research (Wu 1997; Alshawi, Bangalore, and Douglas 2000; Yamada and Knight 2001) that has been fruitful but has not previously produced systems that can compete with phrase-based systems in large-scale…”
Noisy Channel Language Model Prompting for Few-Shot Text Classification (2021, background): “2 While the noisy channel approach has been the most successful in machine translation (Yamada and Knight, 2001; Koehn et al., 2003; Yu et al., 2017; Yee et al., 2019), it has also been studied in more general NLP tasks.”
Bootstrapping parsers via syntactic projection across parallel texts (2005, background): “…the DCA is actually an underlying assumption in most formal attempts to model cross-language correspondences in syntactic relationships (Wu 1995; Alshawi, Bangalore and Douglas 2000; Yamada and Knight 2001; Eisner 2003; Gildea 2003; Melamed, Satta and Wellington 2004; Smith and Smith 2004).”
Tree-to-String Alignment Template for Statistical Machine Translation (2006, background): “Yamada and Knight (2001) use a parser in the target language to train probabilities on a set of operations that transform a target parse tree into a source string.”
Graph-to-Sequence Learning using Gated Graph Neural Networks (2018, background): “MT has a long history of previous work that aims at incorporating syntax (Wu, 1997; Yamada and Knight, 2001; Galley et al., 2004; Liu et al., 2006, inter alia).”
Insertion-based Decoding with Automatically Inferred Generation Order (2019, background): “Another line of work models sequence generation based on syntax structures (Yamada and Knight, 2001; Charniak et al., 2003; Chiang, 2005; Emami and Jelinek, 2005; Zhang et al., 2016; Dyer et al., 2016; Aharoni and Goldberg, 2017; Wang et al., 2018b; Eriguchi et al., 2017).”