Cascaded Phrase-Based Statistical Machine Translation Systems

2009 Seventh Brazilian Symposium in Information and Human Language Technology, 2009

In this paper we describe some experiments carried out to test the impact of automatic casing and punctuation changes when training and testing statistical translation models. The experiments described here concern the translation from/to English and Brazilian Portuguese texts but since the superficial changes investigated are language independent, we believe that the conclusions can be applied to many other pairs of languages. These experiments were designed aiming at setting a baseline scenario for future training and testing of more complex statistical translation models such as the factored ones. From the experiments presented here it is possible to see that case and punctuation changes have a significant impact on automatic translation results.

2003

Abstract In this paper we describe the components of our statistical machine translation system. This system combines phrase-tophrase translations extracted from a bilingual corpus using different alignment approaches. Special methods to extract and align named entities are used. We show how a manual lexicon can be incorporated into the statistical system in an optimized way. Experiments on Chinese-to-English and Arabic-to-English translation tasks are presented.

International Journal of Artificial Intelligence, 2019

Statistical Machine Translation (SMT) is making good progress in recent years. Since SMT systems are based on data-driven approach, they learn from millions or even billions of words from human-translated texts. The quality of SMT systems heavily depends on the data that we use for training step, not only its quality and amount, but also on how relevant it is for the texts that we wish to translate. However, human labeling is very costly and time consuming. In this article we develop a learning mechanism by proposing a round-trip training scenario as a reliable retraining approach through a communication framework for making effective use of monolingual text to tackle the training data scarcity, and improve translation quality. We present detailed experimental results using Spanish-English as a high-resource language pair, and Persian-Spanish as a low-resource language pair. We demonstrate that in all cases translation quality is improved.

2010

Although the scoring features of state-of-theart Phrase-Based Statistical Machine Translation (PB-SMT) models are weighted so as to optimise an objective function measuring translation quality, the estimation of the features themselves does not have any relation to such quality metrics. In this paper, we introduce a translation quality-based feature to PB-SMT in a bid to improve the translation quality of the system. Our feature is estimated by averaging the edit-distance between phrase pairs involved in the translation of oracle sentences, chosen by automatic evaluation metrics from the N -best outputs of a baseline system, and phrase pairs occurring in the N -best list. Using our method, we report a statistically significant 2.11% relative improvement in BLEU score for the WMT 2009 Spanish-to-English translation task. We also report that using our method we can achieve statistically significant improvements over the baseline using many other MT evaluation metrics, and a substantial increase in speed and reduction in memory use (due to a reduction in phrase-table size of 87%) while maintaining significant gains in translation quality.

Proceedings of the Workshop on Exploitation of …, 2010

This paper describes a series of machine translation experiments with the English-Romanian language pair. The experiments were intended to test and prove the hypothesis that syntactically motivated long translation examples added to a base-line 3gram statistically extracted phrase table improves the translation performance in terms of the score BLEU. Extensive tests with a couple of different scenarios were performed: 1) simply concatenating the "extra" translations example to the baseline phrase-table; 2) computing and taking into account perplexities for the POS-string associated to the translation examples; 3) taking into account the number of words in each member of a translation example; 4) filtering the "extra" translation examples by taking into account a score that appreciates the correctness of their lexical alignment. Different combinations of the four scenarios were also tested. Also, the paper presents a method for extracting syntactically motivated translation examples using the dependency linkage of both the source and target sentence. To decompose the source/target sentence into fragments, we identified two types of dependency link-structures -super-links and chains -and used these structures to set the translation example borders.

International Journal of Press-politics, 2009

This paper presents the results of the WMT09 shared tasks, which included a translation task, a system combination task, and an evaluation task. We conducted a large-scale manual evaluation of 87 machine translation systems and 22 system combination entries. We used the ranking of these systems to measure how strongly automatic metrics correlate with human judgments of translation quality, for more than 20 metrics. We present a new evaluation technique whereby system output is edited and judged for correctness.

Language Resources and Evaluation, 2011

This work aims to improve an N-gram-based statistical machine translation system between the Catalan and Spanish languages, trained with an aligned Spanish–Catalan parallel corpus consisting of 1.7 million sentences taken from El Periódico newspaper. Starting from a linguistic error analysis above this baseline system, orthographic, morphological, lexical, semantic and syntactic problems are approached using a set of techniques. The proposed solutions include the development and application of additional statistical techniques, text pre- and post-processing tasks, and rules based on the use of grammatical categories, as well as lexical categorization. The performance of the improved system is clearly increased, as is shown in both human and automatic evaluations of the system, with a gain of about 1.1 points BLEU observed in the Spanish-to-Catalan direction of translation, and a gain of about 0.5 points in the reverse direction. The final system is freely available online as a linguistic resource.

Computational Linguistics, 2013

Translation models used for statistical machine translation are compiled from parallel corpora that are manually translated. The common assumption is that parallel texts are symmetrical: The direction of translation is deemed irrelevant and is consequently ignored. Much research in Translation Studies indicates that the direction of translation matters, however, as translated language (translationese) has many unique properties. It has already been shown that phrase tables constructed from parallel corpora translated in the same direction as the translation task outperform those constructed from corpora translated in the opposite direction. We reconfirm that this is indeed the case, but emphasize the importance of also using texts translated in the “wrong” direction. We take advantage of information pertaining to the direction of translation in constructing phrase tables by adapting the translation model to the special properties of translationese. We explore two adaptation techniqu...

Computational Linguistics, 2009

Universitat Jaume I Current machine translation (MT) systems are still not perfect. In practice, the output from these systems needs to be edited to correct errors. A way of increasing the productivity of the whole translation process (MT plus human work) is to incorporate the human correction activities within the translation process itself, thereby shifting the MT paradigm to that of computer-assisted translation. This model entails an iterative process in which the human translator activity is included in the loop: In each iteration, a prefix of the translation is validated (accepted or amended) by the human and the system computes its best (or n-best) translation suffix hypothesis to complete this prefix. A successful framework for MT is the so-called statistical (or pattern recognition) framework. Interestingly, within this framework, the adaptation of MT systems to the interactive scenario affects mainly the search process, allowing a great reuse of successful techniques and models. In this article, alignment templates, phrase-based models, and stochastic finite-state transducers are used to develop computer-assisted translation systems. These systems were assessed in a European project (TransType2) in two real tasks: The translation of printer manuals; manuals and the translation of the Bulletin of the European Union. In each task, the following three pairs of languages were involved (in both translation directions):