Results 11  20
of
38
Capturing Translational Divergences with a Statistical TreetoTree Aligner
 In Proceedings of the 11th Conference on Theoretical and Methodological Issues in Machine Translation (TMI07
, 2007
"... Parallel treebanks, which comprise paired sourcetarget parse trees aligned at subsentential level, could be useful for many applications, particularly datadriven machine translation. In this paper, we focus on how translational divergences are captured within a parallel treebank using a fully aut ..."
Abstract

Cited by 14 (6 self)
 Add to MetaCart
(Show Context)
Parallel treebanks, which comprise paired sourcetarget parse trees aligned at subsentential level, could be useful for many applications, particularly datadriven machine translation. In this paper, we focus on how translational divergences are captured within a parallel treebank using a fully automatic statistical treetotree aligner. We observe that while the algorithm performs well at the phrase level, performance on lexicallevel alignments is compromised by an inappropriate bias towards coverage rather than precision. This preference for high precision rather than broad coverage in terms of expressing translational divergences through treealignment stands in direct opposition to the situation for SMT wordalignment models. We suggest that this has implications not only for treealignment itself but also for the broader area of induction of syntaxaware models for SMT. 1
A noncontiguous Tree Sequence Alignmentbased Model for Statistical Machine Translation
"... The tree sequence based translation model allows the violation of syntactic boundaries in a rule to capture nonsyntactic phrases, where a tree sequence is a contiguous sequence of subtrees. This paper goes further to present a translation model based on noncontiguous tree sequence alignment, where ..."
Abstract

Cited by 13 (4 self)
 Add to MetaCart
The tree sequence based translation model allows the violation of syntactic boundaries in a rule to capture nonsyntactic phrases, where a tree sequence is a contiguous sequence of subtrees. This paper goes further to present a translation model based on noncontiguous tree sequence alignment, where a noncontiguous tree sequence is a sequence of subtrees and gaps. Compared with the contiguous tree sequencebased model, the proposed model can well handle noncontiguous phrases with any large gaps by means of noncontiguous tree sequence alignment. An algorithm targeting the noncontiguous constituent decoding is also proposed. Experimental results on the NIST MT05 ChineseEnglish translation task show that the proposed model statistically significantly outperforms the baseline systems. 1
Robust Language PairIndependent SubTree Alignment
"... Datadriven approaches to machine translation (MT) achieve stateoftheart results. Many syntaxaware approaches, such as ExampleBased MT and DataOriented Translation, make use of tree pairs aligned at subsentential level. Obtaining subsentential alignments manually is timeconsuming and error ..."
Abstract

Cited by 13 (3 self)
 Add to MetaCart
(Show Context)
Datadriven approaches to machine translation (MT) achieve stateoftheart results. Many syntaxaware approaches, such as ExampleBased MT and DataOriented Translation, make use of tree pairs aligned at subsentential level. Obtaining subsentential alignments manually is timeconsuming and errorprone, and requires expert knowledge of both source and target languages. We propose a novel, language pairindependent algorithm which automatically induces alignments between phrasestructure trees. We evaluate the alignments themselves against a manually aligned gold standard, and perform an extrinsic evaluation by using the aligned data to train and test a DOT system. Our results show that translation accuracy is comparable to that of the same translation system trained on manually aligned data, and coverage improves. 1.
Factorization of synchronous contextfree grammars in linear time
 In NAACL Workshop on Syntax and Structure in Statistical Translation (SSST
, 2007
"... Factoring a Synchronous ContextFree Grammar into an equivalent grammar with a smaller number of nonterminals in each rule enables synchronous parsing algorithms of lower complexity. The problem can be formalized as searching for the treedecomposition of a given permutation with the minimal branchi ..."
Abstract

Cited by 11 (5 self)
 Add to MetaCart
(Show Context)
Factoring a Synchronous ContextFree Grammar into an equivalent grammar with a smaller number of nonterminals in each rule enables synchronous parsing algorithms of lower complexity. The problem can be formalized as searching for the treedecomposition of a given permutation with the minimal branching factor. In this paper, by modifying the algorithm of Uno and Yagiura (2000) for the closely related problem of finding all common intervals of two permutations, we achieve a linear time algorithm for the permutation factorization problem. We also use the algorithm to analyze the maximum SCFG rule length needed to cover handaligned data from various language pairs. 1
Parsers as language models for statistical machine translation
 In Proceedings of AMTA
, 2008
"... Most work in syntaxbased machine translation has been in translation modeling, but there are many reasons why we may instead want to focus on the language model. We experiment with parsers as language models for machine translation in a simple translation model. This approach demands much more of t ..."
Abstract

Cited by 11 (2 self)
 Add to MetaCart
Most work in syntaxbased machine translation has been in translation modeling, but there are many reasons why we may instead want to focus on the language model. We experiment with parsers as language models for machine translation in a simple translation model. This approach demands much more of the language models, allowing us to isolate their strengths and weaknesses. We find that unmodified parsers do not improve BLEU scores over ngram language models, and provide an analysis of their strengths and weaknesses. 1
Comparing Reordering Constraints for SMT Using Efficient BLEU Oracle Computation
"... This paper describes a new method to compare reordering constraints for Statistical Machine Translation. We investigate the best possible (oracle) BLEU score achievable under different reordering constraints. Using dynamic programming, we efficiently find a reordering that approximates the highest a ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
This paper describes a new method to compare reordering constraints for Statistical Machine Translation. We investigate the best possible (oracle) BLEU score achievable under different reordering constraints. Using dynamic programming, we efficiently find a reordering that approximates the highest attainable BLEU score given a reference and a set of reordering constraints. We present an empirical evaluation of popular reordering constraints: local constraints, the IBM constraints, and the Inversion Transduction Grammar (ITG) constraints. We present results for a GermanEnglish translation task and show that reordering under the ITG constraints can improve over the baseline by more than 7.5 BLEU points. 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 6 (1 self)
 Add to MetaCart
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.
MACHINE TRANSLATION BY PATTERN MATCHING
, 2008
"... The best systems for machine translation of natural language are based on statistical models learned from data. Conventional representation of a statistical translation model requires substantial offline computation and representation in main memory. Therefore, the principal bottlenecks to the amoun ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
The best systems for machine translation of natural language are based on statistical models learned from data. Conventional representation of a statistical translation model requires substantial offline computation and representation in main memory. Therefore, the principal bottlenecks to the amount of data we can exploit and the complexity of models we can use are available memory and CPU time, and current state of the art already pushes these limits. With data size and model complexity continually increasing, a scalable solution to this problem is central to future improvement. CallisonBurch et al. (2005) and Zhang and Vogel (2005) proposed a solution that we call translation by pattern matching, which we bring to fruition in this dissertation. The training data itself serves as a proxy to the model; rules and parameters are computed on demand. It achieves our desiderata of minimal offline computation and compact representation, but is dependent on fast pattern matching algorithms on text. They demonstrated its application to a common model based on the translation of contiguous substrings, but leave some open problems. Among these is a question: can this approach match the performance of conventional methods despite unavoidable differences that it induces in the model? We show how to answer this question affirmatively. The main
Empirical lower bounds on alignment error rates in syntaxbased machine translation
 In SSST ’09
, 2009
"... The empirical adequacy of synchronous contextfree grammars of rank two (2SCFGs) (Satta and Peserico, 2005), used in syntaxbased machine translation systems such as Wu (1997), Zhang et al. (2006) and Chiang (2007), in terms of what alignments they induce, has been discussed in Wu (1997) and Welli ..."
Abstract

Cited by 5 (1 self)
 Add to MetaCart
(Show Context)
The empirical adequacy of synchronous contextfree grammars of rank two (2SCFGs) (Satta and Peserico, 2005), used in syntaxbased machine translation systems such as Wu (1997), Zhang et al. (2006) and Chiang (2007), in terms of what alignments they induce, has been discussed in Wu (1997) and Wellington et al. (2006), but with a onesided focus on socalled “insideout alignments”. Other alignment configurations that cannot be induced by 2SCFGs are identified in this paper, and their frequencies across a wide collection of handaligned parallel corpora are examined. Empirical lower bounds on two measures of alignment error rate, i.e. the one introduced in Och and Ney (2000) and one where only complete translation units are considered, are derived for 2SCFGs and related formalisms. 1
Range concatenation grammars for translation
 In Proceedings of COLING
, 2008
"... Positive and bottomup nonerasing binary range concatenation grammars (Boullier, 1998) with at most binary predicates ((2,2)BRCGs) is a O(Gn6) time strict extension of inversion transduction grammars (Wu, 1997) (ITGs). It is shown that (2,2)BRCGs induce insideout alignments (Wu, 1997) and cros ..."
Abstract

Cited by 5 (1 self)
 Add to MetaCart
Positive and bottomup nonerasing binary range concatenation grammars (Boullier, 1998) with at most binary predicates ((2,2)BRCGs) is a O(Gn6) time strict extension of inversion transduction grammars (Wu, 1997) (ITGs). It is shown that (2,2)BRCGs induce insideout alignments (Wu, 1997) and crossserial discontinuous translation units (CDTUs); both phenomena can be shown to occur frequently in many handaligned parallel corpora. A CYKstyle parsing algorithm is introduced, and induction from aligment structures is briefly discussed. Range concatenation grammars (RCG) (Boullier, 1998) mainly attracted attention in the formal language community, since they recognize exactly the polynomial time recognizable languages, but recently they have been argued to be useful for datadriven parsing too (Maier and Søgaard,