Travatar: A Forest-to-String Machine Translation Engine based on Tree Transducers
نویسنده
چکیده
In this paper we describe Travatar, a forest-to-string machine translation (MT) engine based on tree transducers. It provides an open-source C++ implementation for the entire forest-to-string MT pipeline, including rule extraction, tuning, decoding, and evaluation. There are a number of options for model training, and tuning includes advanced options such as hypergraph MERT, and training of sparse features through online learning. The training pipeline is modeled after that of the popular Moses decoder, so users familiar with Moses should be able to get started quickly. We perform a validation experiment of the decoder on EnglishJapanese machine translation, and find that it is possible to achieve greater accuracy than translation using phrase-based and hierarchical-phrase-based translation. As auxiliary results, we also compare different syntactic parsers and alignment techniques that we tested in the process of developing the decoder. Travatar is available under the LGPL at http://phontron.com/travatar
منابع مشابه
A Systematic Evaluation of MBOT in Statistical Machine Translation
Shallow local multi-bottom up tree transducers (MBOTs) have been successfully used as translation models in several settings because of their ability to model discontinuities. In this contribution, several additional settings are explored and evaluated. The first rule extractions for tree-to-tree MBOT with non-minimal rules and for string-to-string MBOT are developed. All existing MBOT systems ...
متن کاملForest-based Tree Sequence to String Translation Model
This paper proposes a forest-based tree sequence to string translation model for syntaxbased statistical machine translation, which automatically learns tree sequence to string translation rules from word-aligned sourceside-parsed bilingual texts. The proposed model leverages on the strengths of both tree sequence-based and forest-based translation models. Therefore, it can not only utilize for...
متن کاملAkamon: An Open Source Toolkit for Tree/Forest-Based Statistical Machine Translation
We describe Akamon, an open source toolkit for tree and forest-based statistical machine translation (Liu et al., 2006; Mi et al., 2008; Mi and Huang, 2008). Akamon implements all of the algorithms required for tree/forestto-string decoding using tree-to-string translation rules: multiple-thread forest-based decoding, n-gram language model integration, beamand cube-pruning, k-best hypotheses ex...
متن کاملString-to-Tree Multi Bottom-up Tree Transducers
We achieve significant improvements in several syntax-based machine translation experiments using a string-to-tree variant of multi bottom-up tree transducers. Our new parameterized rule extraction algorithm extracts string-to-tree rules that can be discontiguous and non-minimal in contrast to existing algorithms for the tree-to-tree setting. The obtained models significantly outperform the str...
متن کاملDependency Forest for Statistical Machine Translation
We propose a structure called dependency forest for statistical machine translation. A dependency forest compactly represents multiple dependency trees. We develop new algorithms for extracting string-todependency rules and training dependency language models. Our forest-based string-to-dependency system obtains significant improvements ranging from 1.36 to 1.46 BLEU points over the tree-based ...
متن کامل