Results 1  10
of
26
A simple and effective hierarchical phrase reordering model
 In Proceedings of EMNLP 2008
, 2008
"... While phrasebased statistical machine translation systems currently deliver stateoftheart performance, they remain weak on word order changes. Current phrase reordering models can properly handle swaps between adjacent phrases, but they typically lack the ability to perform the kind of longdista ..."
Abstract

Cited by 95 (13 self)
 Add to MetaCart
(Show Context)
While phrasebased statistical machine translation systems currently deliver stateoftheart performance, they remain weak on word order changes. Current phrase reordering models can properly handle swaps between adjacent phrases, but they typically lack the ability to perform the kind of longdistance reorderings possible with syntaxbased systems. In this paper, we present a novel hierarchical phrase reordering model aimed at improving nonlocal reorderings, which seamlessly integrates with a standard phrasebased system with little loss of computational efficiency. We show that this model can successfully handle the key examples often used to motivate syntaxbased systems, such as the rotation of a prepositional phrase around a noun phrase. We contrast our model with reordering models commonly used in phrasebased systems, and show that our approach provides statistically significant BLEU point gains for two language pairs: ChineseEnglish (+0.53 on MT05 and +0.71 on MT08) and ArabicEnglish (+0.55 on MT05). 1
Joint Parsing and Translation
"... Treebased translation models, which exploit the linguistic syntax of source language, usually separate decoding into two steps: parsing and translation. Although this separation makes treebased decoding simple and efficient, its translation performance is usually limited by the number of parse tre ..."
Abstract

Cited by 10 (2 self)
 Add to MetaCart
Treebased translation models, which exploit the linguistic syntax of source language, usually separate decoding into two steps: parsing and translation. Although this separation makes treebased decoding simple and efficient, its translation performance is usually limited by the number of parse trees offered by parser. Alternatively, we propose to parse and translate jointly by casting treebased translation as parsing. Given a sourcelanguage sentence, our joint decoder produces a parse tree on the source side and a translation on the target side simultaneously. By combining translation and parsing models in a discriminative framework, our approach significantly outperforms a forestbased treetostring system by 1.1 absolute BLEU points on the NIST 2005 ChineseEnglish test set. As a parser, our joint decoder achieves an F1 score of 80.6 % on the Penn Chinese Treebank. 1
Why Synchronous Tree Substitution Grammars?
"... Synchronous tree substitution grammars are a translation model that is used in syntaxbased machine translation. They are investigated in a formal setting and compared to a competitor that is at least as expressive. The competitor is the extended multi bottomup tree transducer, which is the bottom ..."
Abstract

Cited by 10 (6 self)
 Add to MetaCart
(Show Context)
Synchronous tree substitution grammars are a translation model that is used in syntaxbased machine translation. They are investigated in a formal setting and compared to a competitor that is at least as expressive. The competitor is the extended multi bottomup tree transducer, which is the bottomup analogue with one essential additional feature. This model has been investigated in theoretical computer science, but seems widely unknown in natural language processing. The two models are compared with respect to standard algorithms (binarization, regular restriction, composition, application). Particular attention is paid to the complexity of the algorithms. 1
Constituency to Dependency Translation with Forests
"... Treetostring systems (and their forestbased extensions) have gained steady popularity thanks to their simplicity and efficiency, but there is a major limitation: they are unable to guarantee the grammaticality of the output, which is explicitly modeled in stringtotree systems via targetside synt ..."
Abstract

Cited by 8 (2 self)
 Add to MetaCart
(Show Context)
Treetostring systems (and their forestbased extensions) have gained steady popularity thanks to their simplicity and efficiency, but there is a major limitation: they are unable to guarantee the grammaticality of the output, which is explicitly modeled in stringtotree systems via targetside syntax. We thus propose to combine the advantages of both, and present a novel constituencytodependency 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. Mediumscale experiments show an absolute and statistically significant improvement of +0.7 BLEU points over a stateoftheart forestbased treetostring system even with fewer rules. This is also the first time that a treetotree model can surpass treetostring counterparts. 1
Two monolingual parses are better than one (synchronous parse
 In Proc. of HLTNAACL
, 2010
"... We describe a synchronous parsing algorithm that is based on two successive monolingual parses of an input sentence pair. Although the worstcase complexity of this algorithm is and must be O(n6) for binary SCFGs, its averagecase runtime is far better. We demonstrate that for a number of common sy ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
(Show Context)
We describe a synchronous parsing algorithm that is based on two successive monolingual parses of an input sentence pair. Although the worstcase complexity of this algorithm is and must be O(n6) for binary SCFGs, its averagecase runtime is far better. We demonstrate that for a number of common synchronous parsing problems, the twoparse algorithm substantially outperforms alternative synchronous parsing strategies, making it efficient enough to be utilized without resorting to a pruned search. 1
Asynchronous Binarization for Synchronous Grammars
"... Binarization of nary rules is critical for the efficiency of syntactic machine translation decoding. Because the target side of a rule will generally reorder the source side, it is complex (and sometimes impossible) to find synchronous rule binarizations. However, we show that synchronous binarizat ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
(Show Context)
Binarization of nary rules is critical for the efficiency of syntactic machine translation decoding. Because the target side of a rule will generally reorder the source side, it is complex (and sometimes impossible) to find synchronous rule binarizations. However, we show that synchronous binarizations are not necessary in a twostage decoder. Instead, the grammar can be binarized one way for the parsing stage, then rebinarized in a different way for the reranking stage. Each individual binarization considers only one monolingual projection of the grammar, entirely avoiding the constraints of synchronous binarization and allowing binarizations that are separately optimized for each stage. Compared to nary forest reranking, even simple targetside binarization schemes improve overall decoding accuracy. 1
Grammar Factorization by Tree Decomposition
"... We describe the application of the graphtheoretic property known as treewidth to the problem of finding efficient parsing algorithms. This method, similar to the junction tree algorithm used in graphical models for machine learning, allows automatic discovery of efficient algorithms such as the O(n ..."
Abstract

Cited by 5 (1 self)
 Add to MetaCart
(Show Context)
We describe the application of the graphtheoretic property known as treewidth to the problem of finding efficient parsing algorithms. This method, similar to the junction tree algorithm used in graphical models for machine learning, allows automatic discovery of efficient algorithms such as the O(n 4) algorithm for bilexical grammars of Eisner and Satta. We examine the complexity of applying this method to parsing algorithms for general Linear ContextFree Rewriting Systems. We show that any polynomialtime algorithm for this problem would imply an improved approximation algorithm for the wellstudied treewidth problem on general graphs. 1.
A Generalized View on Parsing and Translation
"... We present a formal framework that generalizes a variety of monolingual and synchronous grammar formalisms for parsing and translation. Our framework is based on regular tree grammars that describe derivation trees, which are interpreted in arbitrary algebras. We obtain generic parsing algorithms by ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
We present a formal framework that generalizes a variety of monolingual and synchronous grammar formalisms for parsing and translation. Our framework is based on regular tree grammars that describe derivation trees, which are interpreted in arbitrary algebras. We obtain generic parsing algorithms by exploiting closure properties of regular tree languages. 1
Optimal Parsing Strategies for Linear ContextFree Rewriting Systems
"... Factorization is the operation of transforming a production in a Linear ContextFree Rewriting System (LCFRS) into two simpler productions by factoring out a subset of the nonterminals on the production’s righthand side. Factorization lowers the rank of a production but may increase its fanout. We ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
Factorization is the operation of transforming a production in a Linear ContextFree Rewriting System (LCFRS) into two simpler productions by factoring out a subset of the nonterminals on the production’s righthand side. Factorization lowers the rank of a production but may increase its fanout. We show how to apply factorization in order to minimize the parsing complexity of the resulting grammar, and study the relationship between rank, fanout, and parsing complexity. We show that it is always possible to obtain optimum parsing complexity with rank two. However, among transformed grammars of rank two, minimum parsing complexity is not always possible with minimum fanout. Applying our factorization algorithm to LCFRS rules extracted from dependency treebanks allows us to find the most efficient parsing strategy for the syntactic phenomena found in nonprojective trees. 1
On the Expressivity of Linear Transductions
"... We investigate the formal expressivity properties of linear transductions, the class of transductions generated by linear transduction grammars, linear inversion transduction grammars and preterminalized linear inversion transduction grammars. While empirical results such as those in previous work a ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
We investigate the formal expressivity properties of linear transductions, the class of transductions generated by linear transduction grammars, linear inversion transduction grammars and preterminalized linear inversion transduction grammars. While empirical results such as those in previous work are of course an ultimate test of modeling adequacy for machine translation applications, it is equally important to understand the formal theoretical properties of any such new representation. An important part of the expressivity of a transduction is the possibility to align tokens between the two languages generated. We refer to the number of different alignments that are allowed under a transduction as its weak alignment capacity. This aspect of expressivity is quantified for linear transductions using preterminalized linear inversion transduction grammars, and compared to the expressivity of finitestate transductions, inversion transductions and syntaxdirected transductions. 1