Tree-to-String Alignment Template for Statistical Machine Translation

By Yang Liu, Qun Liu, Shouxun Lin. Annual Meeting of the Association for Computational Linguistics, 2006

393 citations recorded by the source corpus.

We present a novel translation model based on tree-to-string alignment template (TAT) which describes the alignment between a source parse tree and a target string. A TAT is capable of generating both terminals and non-terminals and performing reordering at both low and high levels. The model is linguistically syntax-based because TATs are extracted automatically from word-aligned, source side parsed parallel texts. To translate a source sentence, we first employ a parser to produce a source parse tree and then apply TATs to transform the tree into a target string. Our experiments show that the TAT-based model significantly outperforms Pharaoh, a state-of-the-art decoder for phrase-based models.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/7e982f360b44094552264010781a476d85ac78a7

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

Chunk-Based Bi-Scale Decoder for Neural Machine Translation (2017, methodology): “Incorporating Syntactic Information in NMT Syntactic information has been widely used in SMT (Liu et al., 2006; Marton and Resnik, 2008; Shen et al., 2008), and a lot of previous work explore to incorporate the syntactic information in NMT, which shows the effectiveness of the syntactic information ”
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, ”
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).”
First- and Second-Order Expectation Semirings with Applications to Minimum-Risk Training on Translation Forests (2009, background): “…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 structures (Chiang, 2007).”
Sequence-to-Dependency Neural Machine Translation (2017, background): “Incorporating linguistic knowledge into machine translation has been extensively studied in Statistic Machine Translation (SMT) (Galley et al., 2006; Shen et al., 2008; Liu et al., 2006).”
NiuTrans: An Open Source Toolkit for Phrase-based and Syntax-based Machine Translation (2012, background): “…paradigms developed over the past decade, and allows for training and decoding with several state-of-the-art models, including: the phrase-based model (Koehn et al., 2003), the hierarchical phrase-based model (Chiang, 2007), and various syntax-based models (Galley et al., 2004; Liu et al., 2006).”
AMR-to-text Generation with Synchronous Node Replacement Grammar (2017, methodology): “Our graph-to-string rules are inspired by synchronous grammars for machine translation (Wu, 1997; Yamada and Knight, 2002; Gildea, 2003; Chiang, 2005; Huang et al., 2006; Liu et al., 2006).”
Deep Neural Machine Translation with Linear Associative Unit (2017, background): “Unlike conventional Statistical Machine Translation (SMT) systems (Koehn et al., 2003; Chi-ang, 2005; Liu et al., 2006; Xiong et al., 2006; Mi et al., 2008) which consist of multiple separately tuned components, NMT aims at building upon a single and large neural network to directly map input text…”
Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder (2017, background): “Although syntax has shown its e ﬀ ectiveness 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. (2016)) process a sentence only as a…”
Learning to Translate with Source and Target Syntax (2010, background): “…simplest of these (Chiang, 2005) make no use of information from syntactic theories or syntactic annotations, whereas others have successfully incorporated syntactic information on the target side (Galley et al., 2004; Galley et al., 2006) or the source side (Liu et al., 2006; Huang et al., 2006).”
Forest Rescoring: Faster Decoding with Integrated Language Models (2007, background): “In tree-to-string (also called syntax-directed ) decoding (Huang et al., 2006; Liu et al., 2006), the source string is ﬁrst parsed into a tree, which is then re-cursively converted into a target string according to transfer rules in a synchronous grammar (Galley et al., 2006).”