Results 1  10
of
15
Rule filtering by pattern for efficient hierarchical translation
 In Proceedings of the EACL
, 2009
"... We describe refinements to hierarchical translation search procedures intended to reduce both search errors and memory usage through modifications to hypothesis expansion in cube pruning and reductions in the size of the rule sets used in translation. Rules are put into syntactic classes based on th ..."
Abstract

Cited by 24 (3 self)
 Add to MetaCart
We describe refinements to hierarchical translation search procedures intended to reduce both search errors and memory usage through modifications to hypothesis expansion in cube pruning and reductions in the size of the rule sets used in translation. Rules are put into syntactic classes based on the number of nonterminals and the pattern, and various filtering strategies are then applied to assess the impact on translation speed and quality. Results are reported on the 2008 NIST ArabictoEnglish evaluation task. 1
A Systematic Analysis of Translation Model Search Spaces
"... Translation systems are complex, and most metrics do little to pinpoint causes of error or isolate system differences. We use a simple technique to discover induction errors, which occur when good translations are absent from model search spaces. Our results show that a common pruning heuristic dras ..."
Abstract

Cited by 20 (2 self)
 Add to MetaCart
Translation systems are complex, and most metrics do little to pinpoint causes of error or isolate system differences. We use a simple technique to discover induction errors, which occur when good translations are absent from model search spaces. Our results show that a common pruning heuristic drastically increases induction error, and also strongly suggest that the search spaces of phrasebased and hierarchical phrasebased models are highly overlapping despite the well known structural differences. 1
Soft Syntactic Constraints for Hierarchical Phrasebased Translation Using Latent Syntactic Distributions
"... In this paper, we present a novel approach to enhance hierarchical phrasebased machine translation systems with linguistically motivated syntactic features. Rather than directly using treebank categories as in previous studies, we learn a set of linguisticallyguided latent syntactic categories aut ..."
Abstract

Cited by 9 (1 self)
 Add to MetaCart
(Show Context)
In this paper, we present a novel approach to enhance hierarchical phrasebased machine translation systems with linguistically motivated syntactic features. Rather than directly using treebank categories as in previous studies, we learn a set of linguisticallyguided latent syntactic categories automatically from a sourceside parsed, wordaligned parallel corpus, based on the hierarchical structure among phrase pairs as well as the syntactic structure of the source side. In our model, each X nonterminal in a SCFG rule is decorated with a realvalued feature vector computed based on its distribution of latent syntactic categories. These feature vectors are utilized at decoding time to measure the similarity between the syntactic analysis of the source side and the syntax of the SCFG rules that are applied to derive translations. Our approach maintains the advantages of hierarchical phrasebased translation systems while at the same time naturally incorporates soft syntactic constraints.
Bayesian extraction of minimal scfg rules for hierarchical phrasebased translation
 In Proceedings of the Sixth Workshop on SMT
, 2011
"... We present a novel approach for extracting a minimal synchronous contextfree grammar (SCFG) for Hierostyle statistical machine translation using a nonparametric Bayesian framework. Our approach is designed to extract rules that are licensed by the word alignments and heuristically extracted phras ..."
Abstract

Cited by 7 (5 self)
 Add to MetaCart
(Show Context)
We present a novel approach for extracting a minimal synchronous contextfree grammar (SCFG) for Hierostyle statistical machine translation using a nonparametric Bayesian framework. Our approach is designed to extract rules that are licensed by the word alignments and heuristically extracted phrase pairs. Our Bayesian model limits the number of SCFG rules extracted, by sampling from the space of all possible hierarchical rules; additionally our informed prior based on the lexical alignment probabilities biases the grammar to extract high quality rules leading to improved generalization and the automatic identification of commonly reused rules. We show that our Bayesian model is able to extract minimal set of hierarchical phrase rules without impacting the translation quality as measured by the BLEU score. 1
Sampling Tree Fragments from Forests
, 1997
"... We study the problem of sampling trees from forests, in the setting where probabilities for each tree may be a function of arbitrarily large tree fragments. This setting extends recent work for sampling to learn Tree Substitution Grammars to the case where the tree structure (TSG derived tree) is no ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
(Show Context)
We study the problem of sampling trees from forests, in the setting where probabilities for each tree may be a function of arbitrarily large tree fragments. This setting extends recent work for sampling to learn Tree Substitution Grammars to the case where the tree structure (TSG derived tree) is not fixed. We develop a Markov chain Monte Carlo algorithm which corrects for the bias introduced by unbalanced forests, and we present experiments using the algorithm to learn Synchronous ContextFree Grammar rules for machine translation. In this application, the forests being sampled represent the set of Hierostyle rules that are consistent with fixed input wordlevel alignments. We demonstrate equivalent machine translation performance to standard techniques but with much smaller grammars. 1.
An OptimalTime Binarization Algorithm for Linear ContextFree Rewriting Systems with FanOut Two
"... Linear contextfree rewriting systems (LCFRSs) are grammar formalisms with the capability of modeling discontinuous constituents. Many applications use LCFRSs where the fanout (a measure of the discontinuity of phrases) is not allowed to be greater than 2. We present an efficient algorithm for tran ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
(Show Context)
Linear contextfree rewriting systems (LCFRSs) are grammar formalisms with the capability of modeling discontinuous constituents. Many applications use LCFRSs where the fanout (a measure of the discontinuity of phrases) is not allowed to be greater than 2. We present an efficient algorithm for transforming LCFRS with fanout at most 2 into a binary form, whenever this is possible. This results in asymptotical runtime improvement for known parsing algorithms for this class. 1
Compact Rule Extraction for Hierarchical Phrasebased Translation
"... This paper introduces two novel approaches for extracting compact grammars for hierarchical phrasebased translation. The first is a combinatorial optimization approach and the second is a Bayesian model over Hiero grammars using Variational Bayes for inference. In contrast to the conventional Hiero ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
(Show Context)
This paper introduces two novel approaches for extracting compact grammars for hierarchical phrasebased translation. The first is a combinatorial optimization approach and the second is a Bayesian model over Hiero grammars using Variational Bayes for inference. In contrast to the conventional Hiero (Chiang, 2007) rule extraction algorithm, our methods extract compact models reducing model size by 17.8 % to 57.6 % without impacting translation quality across several language pairs. The Bayesian model is particularly effective for resourcepoor languages with evidence from KoreanEnglish translation. To the best of our knowledge, this is the first alternative to Hierostyle rule extraction that finds a more compact synchronous grammar without hurting translation performance. 1
Scalable Variational Inference for Extracting Hierarchical Phrasebased Translation Rules ∗
"... We present a VariationalBayes model for learning rules for the Hierarchical phrasebased model directly from the phrasal alignments. Our model is an alternative to heuristic rule extraction in hierarchical phrasebased translation (Chiang, 2007), which uniformly distributes the probability mass to t ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
(Show Context)
We present a VariationalBayes model for learning rules for the Hierarchical phrasebased model directly from the phrasal alignments. Our model is an alternative to heuristic rule extraction in hierarchical phrasebased translation (Chiang, 2007), which uniformly distributes the probability mass to the extracted rules locally. In contrast, in our approach the probability assigned to a rule is globally determined by its contribution towards all phrase pairs and results in a sparser rule set. We also propose a distributed framework for efficiently running inference for realistic MT corpora. Our experiments translating Korean, Arabic and Chinese into English demonstrate that they are able to exceed or retain the performance of baseline hierarchical phrasebased models. 1
LatentVariable Synchronous CFGs for Hierarchical Translation
"... Datadriven refinement of nonterminal categories has been demonstrated to be a reliable technique for improving monolingual parsing with PCFGs. In this paper, we extend these techniques to learn latent refinements of singlecategory synchronous grammars, so as to improve translation performance. ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
Datadriven refinement of nonterminal categories has been demonstrated to be a reliable technique for improving monolingual parsing with PCFGs. In this paper, we extend these techniques to learn latent refinements of singlecategory synchronous grammars, so as to improve translation performance. We compare two estimators for this latentvariable model: one based on EM and the other is a spectral algorithm based on the method of moments. We evaluate their performance on a Chinese–English translation task. The results indicate that we can achieve significant gains over the baseline with both approaches, but in particular the momentsbased estimator is both faster and performs better than EM. 1
A Source Dependency Model for Statistical Machine Translation
"... In the formally syntaxbased MT, a hierarchical tree generated by synchronous CFG rules associates the source sentence with the target sentence. In this paper, we propose a source dependency model to estimate the probability of the hierarchical tree generated in decoding. We develop this source depe ..."
Abstract
 Add to MetaCart
(Show Context)
In the formally syntaxbased MT, a hierarchical tree generated by synchronous CFG rules associates the source sentence with the target sentence. In this paper, we propose a source dependency model to estimate the probability of the hierarchical tree generated in decoding. We develop this source dependency model from wordaligned corpus, without using any linguistically motivated parsing. Our experimental results show that integrating the source dependency model into the formally syntaxbased machine translation significantly improves the performance on ChinesetoEnglish translation tasks. 1