Abstract | Existing work that uses two independently trained SMT systems cannot directly optimize the paraphrase results. |
Abstract | In this paper, we propose a joint learning method of two SMT systems to optimize the process of paraphrase generation. |
Abstract | In addition, a revised BLEU score (called iBLEU) which measures the adequacy and diversity of the generated paraphrase sentence is proposed for tuning parameters in SMT systems . |
Introduction | Thus researchers leverage bilingual parallel data for this task and apply two SMT systems (dual SMT system ) to translate the original sentences into another pivot language and then translate them back into the original language. |
Introduction | Context features are added into the SMT system to improve translation correctness against polysemous. |
Introduction | Previous work employs two separately trained SMT systems the parameters of which are tuned for SMT scheme and therefore cannot directly optimize the paraphrase purposes, for example, optimize the diversity against the input. |
Paraphrasing with a Dual SMT System | Generating sentential paraphrase with the SMT system is done by first translating a source sentence into another pivot language, and then back into the source. |
Paraphrasing with a Dual SMT System | Here, we call these two procedures a dual SMT system . |
Paraphrasing with a Dual SMT System | 2.1 Joint Inference of Dual SMT System |
Abstract | We evaluated our approach on large-scale J apanese-English and English-Japanese machine translation tasks, and show that it can significantly outperform the baseline phrase-based SMT system . |
Conclusion and Future Work | We also expect to explore better way to integrate ranking reorder model into SMT system instead of a simple penalty scheme. |
Experiments | Lexicon features generally continue to improve the RankingSVM accuracy and reduce CLN on training data, but they do not bring further improvement for SMT systems beyond the top 100 most frequent words. |
Integration into SMT system | There are two ways to integrate the ranking reordering model into a phrase-based SMT system : the pre-reorder method, and the decoding time constraint method. |
Introduction | This is usually done in a preprocessing step, and then followed by a standard phrase-based SMT system that takes the reordered source sentence as input to finish the translation. |
Introduction | The ranking model can not only be used in a pre-reordering based SMT system , but also be integrated into a phrase-based decoder serving as additional distortion features. |
Introduction | We evaluated our approach on large-scale J apanese-English and English-Japanese machine translation tasks, and experimental results show that our approach can bring significant improvements to the baseline phrase-based SMT system in both pre-ordering and integrated decoding settings. |
Conclusions | Some SMT systems never get deployed because of legitimate and incompatible concerns of the prospective users and of the training data owners. |
Conclusions | This same method can be easily extended to other resources used by SMT systems , and indeed even beyond SMT itself, whenever similar constraints on data access exist. |
Experiments | We validated our simple implementation using a phrase table of 38,488,777 lines created with the Moses toolkit3(Koehn et al., 2007) phrase-based SMT system , corresponding to 15,764,069 entries |
Introduction | At the same time, the prospective user of the SMT system that could be derived from such TM might be subject to confidentiality constraints on the text stream needing translation, so that sending out text to translate to an SMT system deployed by the owner of the PT is not an option. |
Discussion | Removing redundant words: Mostly, translating redundant words may confuse the SMT system and would be unnecessary. |
Introduction | The translation quality of the SMT system is highly related to the coverage of translation models. |
Introduction | This problem is more serious for online SMT systems in real-world applications. |
Introduction | the input sentences of the SMT system using automatically extracted paraphrase rules which can capture structures on sentence level in addition to paraphrases on the word or phrase level. |
Abstract | (2009) improved a syntactic SMT system by adding as many as ten thousand syntactic features, and used Margin Infused Relaxed Algorithm (MIRA) to train the feature weights. |
Abstract | Our work is based on a phrase-based SMT system . |
Abstract | In a phrase-based SMT system , the total number of parameters of phrase and lexicon translation models, which we aim to learn discriminatively, is very large (see Table 1). |
Ensemble Decoding | As in the Hiero SMT system (Chiang, 2005), the cells which span up to a certain length (i.e. |
Introduction | Common techniques for model adaptation adapt two main components of contemporary state-of-the-art SMT systems : the language model and the translation model. |
Related Work 5.1 Domain Adaptation | In a similar approach, Koehn and Schroeder (2007) use a feature of the factored translation model framework in Moses SMT system (Koehn and Schroeder, 2007) to use multiple alternative decoding paths. |
Related Work 5.1 Domain Adaptation | The Moses SMT system implements (Koehn and Schroeder, |
Conclusions and Future Work | The two models have been integrated into a phrase-based SMT system and evaluated on Chinese-to-English translation tasks using large-scale training data. |
Introduction | Unfortunately they are usually neither correctly translated nor translated at all in many SMT systems according to the error study by Wu and Fung (2009a). |
Introduction | This suggests that conventional leXical and phrasal translation models adopted in those SMT systems are not sufficient to correctly translate predicates in source sentences. |
Related Work | (2011) incorporate source language semantic role labels into a tree-to-string SMT system . |
Inferring a learning curve from mostly monolingual data | For enabling this work we trained a multitude of instances of the same phrase-based SMT system on 30 distinct combinations of language-pair and domain, each with fourteen distinct training sets of increasing size and tested these instances on multiple in—domain datasets, generating 96 learning curves. |
Introduction | This prediction, or more generally the prediction of the learning curve of an SMT system as a function of available in-domain parallel data, is the objective of this paper. |
Introduction | An extensive study across six parametric function families, empirically establishing that a certain three-parameter power-law family is well suited for modeling learning curves for the Moses SMT system when the evaluation score is BLEU. |
Introduction | However, the state-of-the-art SMT systems translate sentences by using sequences of synchronous rules or phrases, instead of translating word by word. |
Topic Similarity Model | Hellinger function is used to calculate distribution distance and is popular in topic model (Blei and Laf-ferty, 2007).1 By topic similarity, we aim to encourage or penalize the application of a rule for a given document according to their topic distributions, which then helps the SMT system make better translation decisions. |
Topic Similarity Model | By incorporating the topic sensitivity model with the topic similarity model, we enable our SMT system to balance the selection of these two types of rules. |