Left-to-right (LR) decoding Watanabe et al. (2006) is a promising decoding algorithm for hierarchical phrase-based translation (Hiero) that visits input spans in arbitrary order producing the output translation in left to right order. This leads to far fewer language model calls. But the constrained SCFG grammar used in LR-Hiero (GNF) with at most two non-terminals is unable to account for some complex phrasal reordering. Allowing more non-terminals in the rules results in a more expressive grammar. LR-decoding can be used to decode with SCFGs with more than two non-terminals, but the CKY decoders used for Hiero systems cannot deal with such expressive grammars due to a blowup in computational complexity. In this paper we present a dynamic programming algorithm for GNF rule extraction which efficiently extracts sentence level SCFG rule sets with an arbitrary number of non-terminals. We analyze the performance of the obtained grammar for statistical machine translation on three language pairs.

The typical training of a hierarchical phrase-based machine translation involves a pipeline of multiple steps where mistakes in early steps of the pipeline are propagated without any scope for rectifying them. Additionally the alignments are trained independent of and without being informed of the end goal and hence are not optimized for translation. We introduce a novel Bayesian iterative-cascade framework for training Hiero-style model that learns the alignments together with the synchronous translation grammar in an iterative setting. Our framework addresses the above mentioned issues and provides an elegant and principled alternative to the existing training pipeline. Based on the validation experiments involving two language pairs, our proposed iterative-cascade framework shows consistent gains over the traditional training pipeline for hierarchical translation.

Recently, there has been interest in automatically generated word classes for improving statistical machine translation (SMT) quality: e.g, (Wuebker et al, 2013). We create new models by replacing words with word classes in features applied during decoding; we call these “coarse models”. We find that coarse versions of the bilingual language models (biLMs) of (Niehues et al, 2011) yield larger BLEU gains than the original biLMs. BiLMs provide phrase-based systems with rich contextual information from the source sentence; because they have a large number of types, they suffer from data sparsity. Niehues et al (2011) mitigated this problem by replacing source or target words with parts of speech (POSs). We vary their approach in two ways: by clustering words on the source or target side over a range of granularities (word clustering), and by clustering the bilingual units that make up biLMs (bitoken clustering). We find that loglinear combinations of the resulting coarse biLMs with each other and with coarse LMs (LMs based on word classes) yield even higher scores than single coarse models. When we add an appealing “generic” coarse configuration chosen on English > French devtest data to four language pairs (keeping the structure fixed, but providing language-pair-specific models for each pair), BLEU gains on blind test data against strong baselines averaged over 5 runs are +0.80 for English > French, +0.35 for French > English, +1.0 for Arabic > English, and +0.6 for Chinese > English.

When a computer-assisted translation (CAT) tool does not find an exact match for the source segment to translate in its translation memory (TM), translators must use fuzzy matches that come from translation units in the translation memory that do not completely match the source segment. We explore the use of a fuzzy-match repair technique called patching to repair translation proposals from a TM in a CAT environment using any available machine translation system, or any external bilingual source, regardless of its internals. Patching attempts to aid CAT tool users by repairing fuzzy matches and proposing improved translations. Our results show that patching improves the quality of translation proposals and reduces the amount of edit operations to perform, especially when a specific set of restrictions is applied.

In this paper, we address the problem of extracting and integrating bilingual terminology into a Statistical Machine Translation (SMT) system for a Computer Aided Translation (CAT) tool scenario. We develop a framework that, taking as input a small amount of parallel in-domain data, gathers domain-specific bilingual terms and injects them in an SMT system to enhance the translation productivity. Therefore, we investigate several strategies to extract and align bilingual terminology, and to embed it into the SMT. We compare two embedding methods that can be easily used at run-time without altering the normal activity of an SMT system: XML markup and the cache-based model. We tested our framework on two different domains showing improvements up to 15% BLEU score points.

Users of Statistical Machine Translation (SMT) sometimes turn to the Web to obtain data to train their systems. One problem with this approach is the potential for “MT contamination”: when large amounts of parallel data are collected automatically, there is a risk that a non-negligible portion consists of machine-translated text. Theoretically, using this kind of data to train SMT systems is likely to reinforce the errors committed by other systems, or even by an earlier versions of the same system. In this paper, we study the effect of MT-contaminated training data on SMT quality, by performing controlled simulations under a wide range of conditions. Our experiments highlight situations in which MT contamination can be harmful, and assess the potential of decontamination techniques.

This paper presents a novel system for sub-sentential alignment of bilingual sentence pairs, however few, using readily-available machine-readable bilingual dictionaries. Performance is evaluated against an existing gold-standard parallel corpus where word alignments are annotated, showing results that are a considerable improvement on a comparable system and on GIZA++ performance for the same corpus. Since naïve application of the system for N languages would require N(N - 1) dictionaries, it is also evaluated using a pivot language, where only 2(N - 1) dictionaries would be required, with surprisingly similar performance. The system is proposed as an alternative to statistical methods, for use with very small corpora or for ‘on-the-fly’ alignment.

In this paper, we describe an effective translation model combination approach based on the estimation of a probabilistic Support Vector Machine (SVM). We collect domain knowledge from both in-domain and general-domain corpora inspired by a commonly used data selection algorithm, which we then use as features for the SVM training. Drawing on previous work on binary-featured phrase table fill-up (Nakov, 2008; Bisazza et al., 2011), we substitute the binary feature in the original work with our probabilistic domain-likeness feature. Later, we design two experiments to evaluate the proposed probabilistic feature-based approach on the French-to-English language pair using data provided at WMT07, WMT13 and IWLST11 translation tasks. Our experiments demonstrate that translation performance can gain significant improvements of up to +0.36 and +0.82 BLEU scores by using our probabilistic feature-based translation model fill-up approach compared with the binary featured fill-up approach in both experiments.

We introduce two document-level features to polish baseline sentence-level translations generated by a state-of-the-art statistical machine translation (SMT) system. One feature uses the word-embedding technique to model the relation between a sentence and its context on the target side; the other feature is a crisp document-level token-type ratio of target-side translations for source-side words to model the lexical consistency in translation. The weights of introduced features are tuned to optimize the sentence- and document-level metrics simultaneously on the basis of Pareto optimality. Experimental results on two different schemes with different corpora illustrate that the proposed approach can efficiently and stably integrate document-level information into a sentence-level SMT system. The best improvements were approximately 0.5 BLEU on test sets with statistical significance.

In this paper, we propose two extensions to the vector space model (VSM) adaptation technique (Chen et al., 2013b) for statistical machine translation (SMT), both of which result in significant improvements. We also systematically compare the VSM techniques to three mixture model adaptation techniques: linear mixture, log-linear mixture (Foster and Kuhn, 2007), and provenance features (Chiang et al., 2011). Experiments on NIST Chinese-to-English and Arabic-to-English tasks show that all methods achieve significant improvement over a competitive non-adaptive baseline. Except for the original VSM adaptation method, all methods yield improvements in the +1.7-2.0 BLEU range. Combining them gives further significant improvements of up to +2.6-3.3 BLEU over the baseline.

Recent years have seen increased interest in adapting translation models to test domains that are known in advance as well as using latent topic representations to adapt to unknown test domains. However, the relationship between domains and latent topics is still somewhat unclear and topic adaptation approaches typically do not make use of domain knowledge in the training data. We show empirically that combining domain and topic adaptation approaches can be beneficial and that topic representations can be used to predict the domain of a test document. Our best combined model yields gains of up to 0.82 BLEU over a domain-adapted translation system and up to 1.67 BLEU over an unadapted system, measured on the stronger of two training conditions.

In this paper we investigate the problem of adapting a machine translation system to the feedback provided by multiple post-editors. It is well know that translators might have very different post-editing styles and that this variability hinders the application of online learning methods, which indeed assume a homogeneous source of adaptation data. We hence propose multi-task learning to leverage bias information from each single post-editors in order to constrain the evolution of the SMT system. A new framework for significance testing with sentence level metrics is described which shows that Multi-Task learning approaches outperforms existing online learning approaches, with significant gains of 1.24 and 1.88 TER score over a strong online adaptive baseline, on a test set of post-edits produced by four translators texts and on a popular benchmark with multiple references, respectively.

Since the effectiveness of MT adaptation relies on the text repetitiveness, the question on how to measure repetitions in a text naturally arises. This work deals with the issue of looking for and evaluating text features that might help the prediction of the impact of MT adaptation on translation quality. In particular, the repetition rate metric, we recently proposed, is compared to other features employed in very related NLP tasks. The comparison is carried out through a regression analysis between feature values and MT performance gains by dynamically adapted versus non-adapted MT engines, on five different translation tasks. The main outcome of experiments is that the repetition rate correlates better than any other considered feature with the MT gains yielded by the online adaptation, although using all features jointly results in better predictions than with any single feature.

The training data size is of utmost importance for statistical machine translation (SMT), since it affects the training time, model size, decoding speed, as well as the system’s overall success. One of the challenges for developing SMT systems for languages with less resources is the limited sizes of the available training data. In this paper, we propose an approach for expanding the training data by including parallel texts from an out-of-domain corpus. Selecting the best out-of-domain sentences for inclusion in the training set is important for the overall performance of the system. Our method is based on first ranking the out-of-domain sentences using a language modeling approach, and then, including the sentences to the training set by using the vocabulary saturation filter technique. We evaluated our approach for the English-Turkish language pair and obtained promising results. Performance improvements of up to +0.8 BLEU points for the English-Turkish translation system are achieved. We compared our results with the translation model combination approaches as well and reported the improvements. Moreover, we implemented our system with dependency parse tree based language modeling in addition to the n-gram based language modeling and reported comparable results.

For the task of online translation of scientific video lectures, using huge models is not possible. In order to get smaller and efficient models, we perform data selection. In this paper, we perform a qualitative and quantitative comparison of several data selection techniques, based on cross-entropy and infrequent n-gram criteria. In terms of BLEU, a combination of translation and language model cross-entropy achieves the most stable results. As another important criterion for measuring translation quality in our application, we identify the number of out-of-vocabulary words. Here, infrequent n-gram recovery shows superior performance. Finally, we combine the two selection techniques in order to benefit from both their strengths.

This paper gives a general review and detailed analysis of China Workshop on Machine Translation (CWMT) Evaluation. Compared with the past CWMT evaluation campaigns, CWMT2013 evaluation is characterized as follows: first, adopting gray-box evaluation which makes the results more replicable and controllable; second, adding one rule-based system as a counterpart; third, carrying out manual evaluations on some specific tasks to give a more comprehensive analysis of the translation errors. Boosted by those new features, our analysis and case study on the evaluation results shows the pros and cons of both rule-based and statistical systems, and reveals some interesting correlations bewteen automatic and manual evaluation metrics on different translation systems.

This paper presents two improvements of language models based on Restricted Boltzmann Machine (RBM) for large machine translation tasks. In contrast to other continuous space approach, RBM based models can easily be integrated into the decoder and are able to directly learn a hidden representation of the n-gram. Previous work on RBM-based language models do not use a shared word representation and therefore, they might suffer of a lack of generalization for larger contexts. Moreover, since the training step is very time consuming, they are only used for quite small copora. In this work we add a shared word representation for the RBM-based language model by factorizing the weight matrix. In addition, we propose an efficient and tailored sampling algorithm that allows us to drastically speed up the training process. Experiments are carried out on two German to English translation tasks and the results show that the training time could be reduced by a factor of 10 without any drop in performance. Furthermore, the RBM-based model can also be trained on large size corpora.

This paper presents a Japanese-to-English statistical machine translation system specialized for patent translation. Patents are practically useful technical documents, but their translation needs different efforts from general-purpose translation. There are two important problems in the Japanese-to-English patent translation: long distance reordering and lexical translation of many domain-specific terms. We integrated novel lexical translation of domain-specific terms with a syntax-based post-ordering framework that divides the machine translation problem into lexical translation and reordering explicitly for efficient syntax-based translation. The proposed lexical translation consists of a domain-adapted word segmentation and an unknown word transliteration. Experimental results show our system achieves better translation accuracy in BLEU and TER compared to the baseline methods.

Combining Translation Memory (TM) with Statistical Machine Translation (SMT) together has been demonstrated to be beneficial. In this paper, we present a discriminative framework which can integrate TM into SMT by incorporating TM-related feature functions. Experiments on English–Chinese and English–French tasks show that our system using TM feature functions only from the best fuzzy match performs significantly better than the baseline phrase- based system on both tasks, and our discriminative model achieves comparable results to those of an effective generative model which uses similar features. Furthermore, with the capacity of handling a large amount of features in the discriminative framework, we propose a method to efficiently use multiple fuzzy matches which brings more feature functions and further significantly improves our system.

In spoken language translation, it is crucial that an automatic speech recognition (ASR) system produces outputs that can be adequately translated by a statistical machine translation (SMT) system. While word error rate (WER) is the standard metric of ASR quality, the assumption that each ASR error type is weighted equally is violated in a SMT system that relies on structured input. In this paper, we outline a statistical framework for analyzing the impact of specific ASR error types on translation quality in a speech translation pipeline. Our approach is based on linear mixed-effects models, which allow the analysis of ASR errors on a translation quality metric. The mixed-effects models take into account the variability of ASR systems and the difficulty of each speech utterance being translated in a specific experimental setting. We use mixed-effects models to verify that the ASR errors that compose the WER metric do not contribute equally to translation quality and that interactions exist between ASR errors that cumulatively affect a SMT system’s ability to translate an utterance. Our experiments are carried out on the English to French language pair using eight ASR systems and seven post-edited machine translation references from the IWSLT 2013 evaluation campaign. We report significant findings that demonstrate differences in the contributions of specific ASR error types toward speech translation quality and suggest further error types that may contribute to translation difficulty.

Translating prepositions is a difficult and under-studied problem in SMT. We present a novel method to improve the translation of prepositions by using noun classes to model their selectional preferences. We compare three variants of noun class information: (i) classes induced from the lexical resource GermaNet or obtained from clusterings based on either (ii) window information or (iii) syntactic features. Furthermore, we experiment with PP rule generalization. While we do not significantly improve over the baseline, our results demonstrate that (i) integrating selectional preferences as rigid class annotation in the parse tree is sub-optimal, and that (ii) clusterings based on window co-occurrence are more robust than syntax-based clusters or GermaNet classes for the task of modeling selectional preferences.

We present a first attempt at predicting the quality of translations produced by human, professional translators. We examine datasets annotated for quality at sentence- and word-level for four language pairs and provide experiments with prediction models for these datasets. We compare the performance of such models against that of models built from machine translations, highlighting a number of challenges in estimating quality and detecting errors in human translations.

Data selection is a common technique for adapting statistical translation models for a specific domain, which has been shown to both improve translation quality and to reduce model size. Selection relies on some in-domain data, of the same domain of the texts expected to be translated. Selecting the sentence-pairs that are most similar to the in-domain data from a pool of parallel texts has been shown to be effective; yet, this approach holds the risk of resulting in a limited coverage, when necessary n-grams that do appear in the pool are less similar to in-domain data that is available in advance. Some methods select additional data based on the actual text that needs to be translated. While useful, this is not always a practical scenario. In this work we describe an extensive exploration of data selection techniques over Arabic to French datasets, and propose methods to address both similarity and coverage considerations while maintaining a limited model size.

This paper conducts a comprehensive study on the use of triangulation for four very low-resource languages: Mawukakan and Maninkakan, Haitian Kreyol and Malagasy. To the best of our knowledge, ours is the first effective translation system for the first two of these languages. We improve translation quality by adding data using pivot languages and exper- imentally compare previously proposed triangulation design options. Furthermore, since the low-resource language pair and pivot language pair data typically come from very different domains, we use insights from domain adaptation to tune the weighted mixture of direct and pivot based phrase pairs to improve translation quality.

We present a machine translation engine that can translate romanized Arabic, often known as Arabizi, into English. With such a system we can, for the first time, translate the massive amounts of Arabizi that are generated every day in the social media sphere but until now have been uninterpretable by automated means. We accomplish our task by leveraging a machine translation system trained on non-Arabizi social media data and a weighted finite-state transducer-based Arabizi-to-Arabic conversion module, equipped with an Arabic character-based n-gram language model. The resulting system allows high capacity on-the-fly translation from Arabizi to English. We demonstrate via several experiments that our performance is quite close to the theoretical maximum attained by perfect deromanization of Arabizi input. This constitutes the first presentation of a high capacity end-to-end social media Arabizi-to-English translation system.

The training data for statistical machine translation are gathered from various sources representing a mixture of domains. In this work, we argue that when translating dialects representing varieties of the same language, a manually assigned data source is not a reliable indicator of the dialect. We resort to automatic dialect classification to refine the training corpora according to the different dialects and build improved dialect specific systems. A fairly standard classifier for Arabic developed within this work achieves state-of-the-art performance, with classification precision above 90%, making it usefully accurate for our application. The classification of the data is then used to distinguish between the different dialects, split the data accordingly, and utilize the new splits for several adaptation techniques. Performing translation experiments on a large scale dialectal Arabic to English translation task, our results show that the classifier generates better contrast between the dialects and achieves superior translation quality than using the original manual corpora splits.

A novel variation of modified KNESER-NEY model using monomial discounting is presented and integrated into the MOSES statistical machine translation toolkit. The language model is trained on a large training set as usual, but its new discount parameters are tuned to the small development set. An in-domain and cross-domain evaluation of the language model is performed based on perplexity, in which sizable improvements are obtained. Additionally, the performance of the language model is also evaluated in several major machine translation tasks including Chinese-to-English. In those tests, the test data is from a (slightly) different domain than the training data. The experimental results indicate that the new model significantly outperforms a baseline model using SRILM in those domain adaptation scenarios. The new language model is thus ideally suited for domain adaptation without sacrificing performance on in-domain experiments.