Syntax Augmented Machine Translation via Chart Parsing

By Andreas Zollmann, Ashish Venugopal. 2006

363 citations recorded by the source corpus.

We present translation results on the shared task "Exploiting Parallel Texts for Statistical Machine Translation" generated by a chart parsing decoder operating on phrase tables augmented and generalized with target language syntactic categories. We use a target language parser to generate parse trees for each sentence on the target side of the bilingual training corpus, matching them with phrase table lattices built for the corresponding source sentence. Considering phrases that correspond to syntactic categories in the parse trees we develop techniques to augment (declare a syntactically motivated category for a phrase pair) and generalize (form mixed terminal and nonterminal phrases) the phrase table into a synchronous bilingual grammar. We present results on the French-to-English task for this workshop, representing significant improvements over the workshop's baseline system. Our translation system is available open-source under the GNU General Public License.

Subfields: Artificial Intelligence

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

Graph Convolutional Encoders for Syntax-aware Neural Machine Translation (2017, neutral): “This goal is in line with claims that rigid syntactic constraints typically hurt MT (Zollmann and Venugopal, 2006; Smith and Eisner, 2006; Chiang, 2010), and, though these claims have been made in the context of traditional MT systems, we believe they are no less valid for NMT. Attention-based NMT…”
Manual and Automatic Evaluation of Machine Translation between European Languages (2006, background): “ID Participant cmu Carnegie Mellon University, USA (Zollmann and Venugopal, 2006) lcc Language Computer Corporation, USA (Olteanu et al.”
Optimizing Statistical Machine Translation for Text Simplification (2016, methodology): “The PPDB is represented as a synchronous context-free grammar (SCFG), which is commonly used as the formalism for syntax-based machine translation (Zollmann and Venugopal, 2006; Chiang, 2007; Weese et al., 2011).”
NiuTrans: An Open Source Toolkit for Phrase-based and Syntax-based Machine Translation (2012, methodology): “To date, several open-source SMT systems (based on either phrase-based models or syntax-based models) have been developed, such as Moses (Koehn et al., 2007), Joshua (Li et al., 2009), SAMT (Zollmann and Venugopal, 2006), Phrasal (Cer et al., 2010), cdec (Dyer et al., 2010), Jane (Vilar et al., 2010”
Constructing Parallel Corpora for Six Indian Languages via Crowdsourcing (2012, methodology): “, 2006) or SAMT (Zollmann and Venugopal, 2006) is exactly to describe such transformations.”
Lattice-based Minimum Error Rate Training for Statistical Machine Translation (2008, methodology): “It is also straightforward to extend the suggested method to hypergraphs and forests as they are used, e.g., in hierarchical and syntax-augmented systems (Chiang, 2005; Zollmann and Venugopal, 2006).”
Investigating the Usefulness of Generalized Word Representations in SMT (2014, methodology): “A whole new paradigm of using syntactic annotation to address long range reorderings has emerged following Galley et al. (2006), Zollmann and Venugopal (2006), Chiang (2007) etc. Crego and Yvon (2010) and Niehues et al. (2011) used a Tuple Sequence Model (TSM) over POS tags in an N-gram-based…”
Learning to Translate with Source and Target Syntax (2010, methodology): “Drawing on previous successful attempts to relax syntactic constraints during grammar extraction in various ways (Zhang et al., 2008; Liu et al., 2009; Zollmann and Venugopal, 2006), we compare several methods for extracting a synchronous grammar from tree-to-tree data.”
Combining Word Reordering Methods on different Linguistic Abstraction Levels for Statistical Machine Translation (2013, methodology): “Syntax-based (Yamada and Knight, 2001) or syntax-augmented (Zollmann and Venugopal, 2006) MT systems address the reordering problem by embedding syntactic analysis in the decoding process.”