Corpus ID: 1945213

Augmenting String-to-Tree Translation Models with Fuzzy Use of Source-side Syntax

@inproceedings{Zhang2011AugmentingST,
  title={Augmenting String-to-Tree Translation Models with Fuzzy Use of Source-side Syntax},
  author={Jiajun Zhang and Feifei Zhai and Chengqing Zong},
  booktitle={EMNLP},
  year={2011}
}
Due to its explicit modeling of the grammaticality of the output via target-side syntax, the string-to-tree model has been shown to be one of the most successful syntax-based translation models. However, a major limitation of this model is that it does not utilize any useful syntactic information on the source side. In this paper, we analyze the difficulties of incorporating source syntax in a string-to-tree model. We then propose a new way to use the source syntax in a fuzzy manner, both in… Expand
Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features
TLDR
A tree-to-tree machine translation system inspired by quasi-synchronous grammar is presented that combines phrases and dependency syntax, integrating the advantages of phrase-based and syntax-based translation. Expand
Syntax-Based Translation With Bilingually Lexicalized Synchronous Tree Substitution Grammars
TLDR
Both small- and large-scale experiments on Chinese-to-English translation demonstrate that the proposed lexicalized STSG can provide superior rule selection in decoding and substantially improve the translation quality. Expand
Preference Grammars and Soft Syntactic Constraints for GHKM Syntax-based Statistical Machine Translation
TLDR
The results suggest that preference grammars for GHKM translation are inferior to the plain targetsyntactified model, whereas the enhancement with soft source syntactic constraints provides consistent gains. Expand
Explorer Preference Grammars and Soft Syntactic Constraints for GHKM Syntax-based Statistical Machine Translation
In this work, we investigate the effectiveness of two techniques for a featurebased integration of syntactic information into GHKM string-to-tree statistical machine translation (Galley et al.,Expand
Simple but Effective Approaches to Improving Tree-to-tree Model
TLDR
Two simple but effective approaches to overcome the constraints of tree-to-tree translation model are proposed: utilizing fuzzy matching and category translating to integrate bilingual phrases and using head-out binarization to binarize the bilingual parsing trees. Expand
Tree-based Translation without using Parse Trees
TLDR
This paper makes a great effort to bypass the parse trees and induce effective unsupervised trees for treebased translation models and results have shown that the string-to-tree translation system using the unsuper supervised trees significantly outperforms the string to-tree system using parse trees. Expand
Unification-based constraints for statistical machine translation
TLDR
A framework that extends a state-of-the-art syntax-based model with a feature structure lexicon and unification-based constraints on the target-side of the synchronous grammar is proposed and focused on problems in the translation of English to German, a language pair that has a high degree of syntactic reordering and rich target- side morphology. Expand
Influence of Part-of-Speech and Phrasal Category Universal Tag-set in Tree-to-Tree Translation Models
TLDR
A unified tagset for all languages at Part-of-Speech and Phrasal Category level in tree-to-tree models is presented. Expand
Discriminative Feature-Rich Modeling for Syntax-Based Machine Translation
TLDR
A first machine translation system based on quasi-synchronous phrase dependency grammar is presented, which unifies rules from these two categories in a single model and seeks to unify disparate translation models. Expand
Machine Translation by Modeling Predicate-Argument Structure Transformation
TLDR
Experimental results show that the PAS-based translation framework significantly improves the translation performance and effectively models both semantics of languages and global reordering for translation. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 37 REFERENCES
Constituency to Dependency Translation with Forests
TLDR
This work proposes a novel constituency-to-dependency translation model, which uses constituency forests on the source side to direct the translation, and dependency trees on the target side (as a language model) to ensure grammaticality. Expand
A Syntax-Directed Translator with Extended Domain of Locality
TLDR
A syntax-directed translator first parses the source-language input into a parse-tree, and then recursively converts the tree into a string in the target-language, which gives the system more expressive power and flexibility. Expand
Non-Isomorphic Forest Pair Translation
TLDR
This paper proposes a novel non-isomorphic translation framework to capture more non- isomorphic structure mappings than traditional tree-based and tree-sequence-based translation methods, and proposes a parallel space searching method to generate hypothesis using tree-to-string model and evaluate its syntactic goodness using tree to tree/tree sequence model. Expand
Soft Syntactic Constraints for Hierarchical Phrase-Based Translation Using Latent Syntactic Distributions
TLDR
This paper learns a set of linguistically-guided latent syntactic categories automatically from a source-side parsed, word-aligned parallel corpus, based on the hierarchical structure among phrase pairs as well as the syntactic structure of the source side. Expand
Forest-based Tree Sequence to String Translation Model
TLDR
A forest-based tree sequence to string translation model for syntax-based statistical machine translation, which automatically learns tree sequenceto string translation rules from word-aligned source-side-parsed bilingual texts, which statistically significantly outperforms the four baseline systems. Expand
Forest-Based Translation
TLDR
A forest-based approach that translates a packed forest of exponentially many parses, which encodes many more alternatives than standard n-best lists, which takes even less time to translate. Expand
Tree-to-String Alignment Template for Statistical Machine Translation
TLDR
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 that significantly outperforms Pharaoh, a state-of-the-art decoder for phrase-based models. Expand
Scalable Inference and Training of Context-Rich Syntactic Translation Models
TLDR
This paper takes the framework for acquiring multi-level syntactic translation rules of (Galley et al., 2004) from aligned tree-string pairs, and presents two main extensions of their approach: instead of merely computing a single derivation that minimally explains a sentence pair, a large number of derivations that include contextually richer rules, and account for multiple interpretations of unaligned words. Expand
Syntax Augmented Machine Translation via Chart Parsing
TLDR
This work uses 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. Expand
Learning to Translate with Source and Target Syntax
TLDR
This work discusses the reasons why this has been a challenge, reviews existing attempts to meet this challenge, and shows how some old and new ideas can be combined into a simple approach that uses both source and target syntax for significant improvements in translation accuracy. Expand
...
1
2
3
4
...