What’s in a translation rule?

By Michel Galley, Mark Hopkins, Kevin Knight, Daniel Marcu. North American Chapter of the Association for Computational Linguistics, 2004

559 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/a7e925a65860e90b2b4eb427a8bc497f76b2fe6e

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

Towards String-To-Tree Neural Machine Translation (2017, methodology): “We can use this information to extract GHKM rules (Galley et al., 2004).”
Edinburgh’s Syntax-Based Systems at WMT 2014 (2014, methodology): “The grammar was extracted from the word-aligned parallel data using the Moses implementation (Williams and Koehn, 2012) of the GHKM algorithm (Galley et al., 2004; Galley et al., 2006).”
Probabilistic grammars and hierarchical Dirichlet processes (2018, background): “These trees play a central role in a range of activities in modern NLP, including machine translation (Galley et al., 2004), semantic role extraction (Gildea and Jurafsky, 2002), and question answering (Hermjakob, 2001), just to name a few.”
EU-BRIDGE MT: Combined Machine Translation (2014, methodology): “UEDIN’s syntax-based systems (Williams et al., 2014) follow the GHKM syntax approach as proposed by G alley, H opkins, K night, and M arcu (Galley et al., 2004).”
Tree-to-String Alignment Template for Statistical Machine Translation (2006, background): “Similarly to (Galley et al., 2004), the tree-to-string alignment templates discussed in this paper are actually transformation rules.”
Predicting Target Language CCG Supertags Improves Neural Machine Translation (2017, background): “…machine translation (SMT) to capture dependencies between distant words that impact morphological agreement, subcategorisation and word order (Galley et al., 2004; Menezes and Quirk, 2007; Williams and Koehn, 2012; Nadejde et al., 2013; Sennrich, 2015; Nadejde et al., 2016a,b; Chiang, 2007).”
Does String-Based Neural MT Learn Source Syntax? (2016, background): “Nonneural machine translation systems consist chiefly of phrase-based systems (Koehn et al., 2003) and syntax-based systems (Galley et al., 2004; Galley et al., 2006; DeNeefe et al., 2007; Liu et al., 2011; Cowan et al., 2006), the latter of which adds syntactic information to source side…”
Learning to Generate Pseudo-Code from Source Code Using Statistical Machine Translation (T) (2015, unknown): “1) Head Insertion: First, we append a new edge called “HEAD” into the abstract syntax tree, which include the label of inner nodes as their leaves.”
Clause Restructuring for Statistical Machine Translation (2005, background): “A number of researchers (Alshawi, 1996; Wu, 1997; Yamada and Knight, 2001; Gildea, 2003; Melamed, 2004; Graehl and Knight, 2004; Galley et al., 2004) have proposed models where the translation process involves syntactic representations of the source and/or target languages.”
Tuning as Ranking (2011, methodology): “Our syntax-based system (hereafter, SBMT) follows the model of Galley et al. (2004).”
Sentence Compression Beyond Word Deletion (2008, methodology): “We obtain the elementary trees and foreign strings using the GKHM algorithm (Galley et al., 2004).”
Transfer Learning for Low-Resource Neural Machine Translation (2016, methodology): “Table 1 shows that for 4 low-resource languages, a standard stringto-tree statistical MT system (SBMT) (Galley et al., 2004; Galley et al., 2006) strongly outperforms NMT, even when NMT uses the state-of-the-art local attention plus feed-input techniques from Luong et al. (2015a).”
Advances in natural language processing (2015, background): “, their syntax) in translation systems (7, 8), and researchers are actively building deeper meaning representations of language (9) to enable a new level of semantic MT.”
Semantic Parsing with Semi-Supervised Sequential Autoencoders (2016, background): “Semantic parsing is a well-studied problem with numerous approaches including inductive logic programming (Zelle and Mooney, 1996), string-to-tree (Galley et al., 2004) and string-to-graph (Jones et al., 2012) transducers, grammar induction (Kwiatkowski et al., 2011; Artzi and Zettlemoyer, 2013;…”
Posterior Regularization for Structured Latent Variable Models (2010, background): “…for extracting minimal translation units for machine translation, for example, phrases in phrase-based translation systems (Koehn et al., 2003) and rules in syntax-based machine translation (Galley et al., 2004; Chiang et al., 2005), as well as for MT system combination (Matusov et al., 2006).”
Bayesian Symbol-Refined Tree Substitution Grammars for Syntactic Parsing (2012, methodology): “The resulting syntactic analysis can be used for various applications such as machine translation (Galley et al., 2004; DeNeefe and Knight, 2009), sentence compression (Cohn and La-pata, 2009; Yamangil and Shieber, 2010), and question answering (Wang et al., 2007).”