Results 1  10
of
10
Translation as weighted deduction
 In Proc. of EACL
, 2009
"... We present a unified view of many translation algorithms that synthesizes work on deductive parsing, semiring parsing, and efficient approximate search algorithms. This gives rise to clean analyses and compact descriptions that can serve as the basis for modular implementations. We illustrate this w ..."
Abstract

Cited by 11 (3 self)
 Add to MetaCart
We present a unified view of many translation algorithms that synthesizes work on deductive parsing, semiring parsing, and efficient approximate search algorithms. This gives rise to clean analyses and compact descriptions that can serve as the basis for modular implementations. We illustrate this with several examples, showing how to build search spaces for several disparate phrasebased search strategies, integrate nonlocal features, and devise novel models. Although the framework is drawn from parsing and applied to translation, it is applicable to many dynamic programming problems arising in natural language processing and other areas. 1
A Comparison of Various Types of Extended Lexicon Models for Statistical Machine Translation
 In Conf. of the Assoc. for Machine Translation in the Americas (AMTA
, 2010
"... In this work we give a detailed comparison of the impact of the integration of discriminative and triggerbased lexicon models in stateoftheart hierarchical and conventional phrasebased statistical machine translation systems. As both types of extended lexicon models can grow very large, we apply ..."
Abstract

Cited by 6 (4 self)
 Add to MetaCart
In this work we give a detailed comparison of the impact of the integration of discriminative and triggerbased lexicon models in stateoftheart hierarchical and conventional phrasebased statistical machine translation systems. As both types of extended lexicon models can grow very large, we apply certain restrictions to discard some of the less useful information. We show how these restrictions facilitate the training of the extended lexicon models. We finally evaluate systems that incorporate both types of models with different restrictions on a largescale translation task for the ArabicEnglish language pair. Our results suggest that extended lexicon models can be substantially reduced in size while still giving clear improvements in translation performance. 1
Assessing PhraseBased Translation Models with Oracle Decoding
"... Extant Statistical Machine Translation (SMT) systems are very complex softwares, which embed multiple layers of heuristics and embark very large numbers of numerical parameters. As a result, it is difficult to analyze output translations and there is a real need for tools that could help developers ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
Extant Statistical Machine Translation (SMT) systems are very complex softwares, which embed multiple layers of heuristics and embark very large numbers of numerical parameters. As a result, it is difficult to analyze output translations and there is a real need for tools that could help developers to better understand the various causes of errors. In this study, we make a step in that direction and present an attempt to evaluate the quality of the phrasebased translation model. In order to identify those translation errors that stem from deficiencies in the phrase table (PT), we propose to compute the oracle BLEU4 score, that is the best score that a system based on this PT can achieve on a reference corpus. By casting the computation of the oracle BLEU1 as an Integer Linear Programming (ILP) problem, we show that it is possible to efficiently compute accurate lowerbounds of this score, and report measures performed on several standard benchmarks. Various other applications of these oracle decoding techniques are also reported and discussed.
Verb
"... The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing search errors. Second, all distortion is penalized linearly, even when appropriate reorderings are performed. Because the co ..."
Abstract
 Add to MetaCart
The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing search errors. Second, all distortion is penalized linearly, even when appropriate reorderings are performed. Because the cost function does not effectively constrain search, translation quality decreases at higher distortion limits, which are often needed when translating between languages of different typologies such as Arabic and English. To address these problems, we introduce a method for estimating future linear distortion cost, and a new discriminative distortion model that predicts word movement during translation. In combination, these extensions give a statistically significant improvement over a baseline distortion parameterization. When we triple the distortion limit, our model achieves a +2.32 BLEU average gain over Moses. 1
Automatically Improved Category Labels for SyntaxBased Statistical Machine Translation
, 2011
"... A common modeling choice in syntaxbased statistical machine translation is the use of synchronous contextfree grammars, or SCFGs. When training a translation model in a supervised setting, an SCFG is extracted from parallel text that has been statistically wordaligned and parsed by monolingual st ..."
Abstract
 Add to MetaCart
A common modeling choice in syntaxbased statistical machine translation is the use of synchronous contextfree grammars, or SCFGs. When training a translation model in a supervised setting, an SCFG is extracted from parallel text that has been statistically wordaligned and parsed by monolingual statistical parsers. However, the set of syntactic category labels used in a monolingual statistical parser is decided upon quite independently of the machine translation task, and there is no guarantee that it is optimal for a bilingual SCFG or for machine translation at all. In this thesis, we first demonstrate that the set of category labels used in a machine translation system’s grammar strongly affects three interrelated characteristics of the system: spurious ambiguity, rule sparsity, and reordering precision. We propose using these characteristics as the basis for evaluating the properties of an SCFG both outside of and within an actual translation task. Finally, as our main work, we propose three automatic relabeling methods that will create a better set of category labels for a given language pair
Computing Lattice BLEU Oracle Scores for Machine Translation
"... The search space of PhraseBased Statistical Machine Translation (PBSMT) systems can be represented under the form of a directed acyclic graph (lattice). The quality of this search space can thus be evaluated by computing the best achievable hypothesis in the lattice, the socalled oracle hypothesis ..."
Abstract
 Add to MetaCart
The search space of PhraseBased Statistical Machine Translation (PBSMT) systems can be represented under the form of a directed acyclic graph (lattice). The quality of this search space can thus be evaluated by computing the best achievable hypothesis in the lattice, the socalled oracle hypothesis. For common SMT metrics, this problem is however NPhard and can only be solved using heuristics. In this work, we present two new methods for efficiently computing BLEU oracles on lattices: the first one is based on a linear approximation of the corpus BLEU score and is solved using the FST formalism; the second one relies on integer linear programming formulation and is solved directly and using the Lagrangian relaxation framework. These new decoders are positively evaluated and compared with several alternatives from the literature for three language pairs, using lattices produced by two PBSMT systems. 1
A Detailed Analysis of Phrasebased and Syntaxbased Machine Translation: The Search for Systematic Differences
"... This paper describes a range of automatic and manual comparisons of phrasebased and syntaxbased statistical machine translation methods applied to EnglishGerman and EnglishFrench translation of usergenerated content. The syntaxbased methods underperform the phrasebased models and the relaxati ..."
Abstract
 Add to MetaCart
This paper describes a range of automatic and manual comparisons of phrasebased and syntaxbased statistical machine translation methods applied to EnglishGerman and EnglishFrench translation of usergenerated content. The syntaxbased methods underperform the phrasebased models and the relaxation of syntactic constraints to broaden translation rule coverage means that these models do not necessarily generate output which is more grammatical than the output produced by the phrasebased models. Although the systems generate different output and can potentially be fruitfully combined, the lack of systematic difference between these models makes the combination task more challenging. 1
Verb
"... The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing search errors. Second, all distortion is penalized linearly, even when appropriate reorderings are performed. Because the co ..."
Abstract
 Add to MetaCart
The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing search errors. Second, all distortion is penalized linearly, even when appropriate reorderings are performed. Because the cost function does not effectively constrain search, translation quality decreases at higher distortion limits, which are often needed when translating between languages of different typologies such as Arabic and English. To address these problems, we introduce a method for estimating future linear distortion cost, and a new discriminative distortion model that predicts word movement during translation. In combination, these extensions give a statistically significant improvement over a baseline distortion parameterization. When we triple the distortion limit, our model achieves a +2.32 BLEU average gain over Moses. 1
Verb
"... The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing search errors. Second, all distortion is penalized linearly, even when appropriate reorderings are performed. Because the co ..."
Abstract
 Add to MetaCart
The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing search errors. Second, all distortion is penalized linearly, even when appropriate reorderings are performed. Because the cost function does not effectively constrain search, translation quality decreases at higher distortion limits, which are often needed when translating between languages of different typologies such as Arabic and English. To address these problems, we introduce a method for estimating future linear distortion cost, and a new discriminative distortion model that predicts word movement during translation. In combination, these extensions give a statistically significant improvement over a baseline distortion parameterization. When we triple the distortion limit, our model achieves a +2.32 BLEU average gain over Moses. 1
U N I V E R
, 2009
"... The arguably best performing statistical machine translation systems are based on contextfree formalisms or weakly equivalent ones. These models usually use a synchronous version of a contextfree grammar (SCFG) which we argue is too rigid for the highly ambiguous task of human language translation ..."
Abstract
 Add to MetaCart
The arguably best performing statistical machine translation systems are based on contextfree formalisms or weakly equivalent ones. These models usually use a synchronous version of a contextfree grammar (SCFG) which we argue is too rigid for the highly ambiguous task of human language translation. This is exacerbated by the fact that the imperfect methods available for aligning parallel texts make extracting an efficient grammar very hard. As a result, the contextfree grammars extracted are usually very large in size after having already been restricted through a variety of constraints. We propose to use Combinatorial Categorial Grammar (CCG) for machine translation models. CCG is a lexicalized, mildlycontextsensitive formalism which is very well suited to capture longdistance dependencies that are not addressed very well by most current models. We believe that CCG is very well suited for the task of machine translation due to its ability to represent nonconstituents in a syntactic way which frequently occur in parallel texts as well as its high derivational flexibility. This allows us to use some of the advantages of nonsyntactic phrasebased approaches within a syntactic framework such as a relatively small grammar size compared to contextfreebased