KyotoEBMT: An Example-Based Dependency-to-Dependency Translation Framework

Richardson, John T. E.; Cromierès, Fabien; Nakazawa, Toshiaki; Kurohashi, Sadao

doi:10.3115/v1/p14-5014

Cited by 6 publications

(9 citation statements)

References 8 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used a state-of-the-art dependency tree-to-tree decoder (Richardson et al, 2014) with the default settings. The neural network is constructed and trained using the Chainer (Tokui et al, 2015).…”

Section: Methodsmentioning

confidence: 99%

“…However, we believe that using target-side syntax is important to achieve highquality translations between distant language pairs which require long range reorderings. Especially, using dependency trees on both source and target sides is promising for this purpose (Menezes and Quirk, 2007;Nakazawa and Kurohashi, 2010;Richardson et al, 2014). Tree-based translation models naturally realize word reorderings using the non-terminals or anchors for the attachment in the translation rules: therefore they do not need a reordering model which string-based models require.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Insertion Position Selection Model for Flexible Non-Terminals in Dependency Tree-to-Tree Machine Translation

Nakazawa

Richardson

Kurohashi

2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

Dependency tree-to-tree translation models are powerful because they can naturally handle long range reorderings which is important for distant language pairs. The translation process is easy if it can be accomplished only by replacing non-terminals in translation rules with other rules. However it is sometimes necessary to adjoin translation rules. Flexible non-terminals have been proposed as a promising solution for this problem. A flexible non-terminal provides several insertion position candidates for the rules to be adjoined, but it increases the computational cost of decoding. In this paper we propose a neural network based insertion position selection model to reduce the computational cost by selecting the appropriate insertion positions. The experimental results show the proposed model can select the appropriate insertion position with a high accuracy. It reduces the decoding time and improves the translation quality owing to reduced search space.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Insertion Position Selection Model for Flexible Non-Terminals in Dependency Tree-to-Tree Machine Translation

Nakazawa

Richardson

Kurohashi

2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Figure 1 shows an example of three rules that can be extracted from aligned and parsed sentence pairs. In this paper we consider rules similar to previous work on tree-to-tree dependency MT (Richardson et al, 2014). The simplest type of rule, containing only terminal symbols, can be extracted trivially from aligned subtrees (see rules 2 and 3 in Figure 1).…”

Section: Dependency Tree-to-tree Translationmentioning

confidence: 99%

Flexible Non-Terminals for Dependency Tree-to-Tree Reordering

Richardson

Cromierès

Nakazawa

et al. 2016

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

Self Cite

View full text Add to dashboard Cite

A major benefit of tree-to-tree over treeto-string translation is that we can use target-side syntax to improve reordering. While this is relatively simple for binarized constituency parses, the reordering problem is considerably harder for dependency parses, in which words can have arbitrarily many children. Previous approaches have tackled this problem by restricting grammar rules, reducing the expressive power of the translation model.In this paper we propose a general model for dependency tree-to-tree reordering based on flexible non-terminals that can compactly encode multiple insertion positions. We explore how insertion positions can be selected even in cases where rules do not entirely cover the children of input sentence words. The proposed method greatly improves the flexibility of translation rules at the cost of only a 30% increase in decoding time, and we demonstrate a 1.2-1.9 BLEU improvement over a strong tree-to-tree baseline.

show abstract

“…This work was developed mainly in the context of a syntactic-dependency-based tree-to-tree translation system described in (Richardson et al, 2014). Although it is a tree-to-tree system, we simplify the decoding step by "flattening" the target-side tree translation rules into string expansion rules (keeping track of the dependency structure in state features).…”

Section: Settingmentioning

confidence: 99%

Translation Rules with Right-Hand Side Lattices

Cromierès

Kurohashi

2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

In Corpus-Based Machine Translation, the search space of the translation candidates for a given input sentence is often defined by a set of (cyclefree) context-free grammar rules. This happens naturally in Syntax-Based Machine Translation and Hierarchical Phrase-Based Machine Translation (where the representation will be the set of the target-side half of the synchronous rules used to parse the input sentence). But it is also possible to describe Phrase-Based Machine Translation in this framework. We propose a natural extension to this representation by using lattice-rules that allow to easily encode an exponential number of variations of each rules. We also demonstrate how the representation of the search space has an impact on decoding efficiency, and how it is possible to optimize this representation.

show abstract

KyotoEBMT: An Example-Based Dependency-to-Dependency Translation Framework

Cited by 6 publications

References 8 publications

Insertion Position Selection Model for Flexible Non-Terminals in Dependency Tree-to-Tree Machine Translation

Insertion Position Selection Model for Flexible Non-Terminals in Dependency Tree-to-Tree Machine Translation

Flexible Non-Terminals for Dependency Tree-to-Tree Reordering

Translation Rules with Right-Hand Side Lattices

Contact Info

Product

Resources

About