Jan-Thorsten Peter

Can We Translate Letters

Current statistical machine translation systems handle the translation process as the transformation of a string of symbols into another string of symbols. Normally the symbols dealt with are the words in different languages, sometimes with some additional information included, like morphological data. In this work we try to push the approach to the limit, working not on the level of words, but treating both the source and target sentences as a string of letters. We try to find out if a nearly unmodified state-of-the-art translation system is able to cope with the problem and whether it is capable to further generalize translation rules, for example at the level of word suffixes and translation of unseen words. Experiments are carried out for the translation of Catalan to Spanish.

A Comparison between Count and Neural Network Models Based on Joint Translation and Reordering Sequences

We propose a conversion of bilingual sentence pairs and the corresponding word alignments into novel linear sequences. These are joint translation and reordering (JTR) uniquely defined sequences, combining interdepending lexical and alignment dependencies on the word level into a single framework. They are constructed in a simple manner while capturing multiple alignments and empty words. JTR sequences can be used to train a variety of models. We investigate the performances of ngram models with modified Kneser-Ney smoothing, feed-forward and recurrent neural network architectures when estimated on JTR sequences, and compare them to the operation sequence model (Durrani et al., 2013b). Evaluations on the IWSLT German!English, WMT German!English and BOLT Chinese!English tasks show that JTR models improve state-of-the-art phrasebased systems by up to 2.2 BLEU.

CharacTer: Translation Edit Rate on Character Level.

Recently, the capability of character-level evaluation measures for machine translation output has been confirmed by several metrics. This work proposes translation edit rate on character level (CharacTER), which calculates the character level edit distance while performing the shift edit on word level. The novel metric shows high system-level correlation with human rankings, especially for morphologically rich languages. It outperforms the strong CHRF by up to 7% correlation on different metric tasks. In addition, we apply the hypothesis sentence length for normalizing the edit distance in CharacTER, which also provides significant improvements compared to using the reference sentence length.

Hierarchical Phrase-Based Translation with Jane 2

Hierarchical Phrase-Based Translation with Jane 2 In this paper, we give a survey of several recent extensions to hierarchical phrase-based machine translation that have been implemented in version 2 of Jane, RWTHs open source statistical machine translation toolkit. We focus on the following techniques: Insertion and deletion models, lexical scoring variants, reordering extensions with non-lexicalized reordering rules and with a discriminative lexicalized reordering model, and soft string-to-dependency hierarchical machine translation. We describe the fundamentals of each of these techniques and present experimental results obtained with Jane 2 to confirm their usefulness in state-of-the-art hierarchical phrase-based translation (HPBT).

A Linguistic Evaluation of Rule-Based, Phrase-Based, and Neural MT Engines

Abstract In this paper, we report an analysis of the strengths and weaknesses of several Machine Translation (MT) engines implementing the three most widely used paradigms. The analysis is based on a manually built test suite that comprises a large range of linguistic phenomena. Two main observations are on the one hand the striking improvement of an commercial online system when turning from a phrase-based to a neural engine and on the other hand that the successful translations of neural MT systems sometimes bear resemblance with the translations of a rule-based MT system.

The QT21/HimL Combined Machine Translation System

This paper describes the joint submission of the QT21 and HimL projects for the English→Romanian translation task of the ACL 2016 First Conference on Machine Translation (WMT 2016). The submission is a system combination which combines twelve different statistical machine translation systems provided by the different groups (RWTH Aachen University, LMU Munich, Charles University in Prague, University of Edinburgh, University of Sheffield, Karlsruhe Institute of Technology, LIMSI, University of Amsterdam, Tilde). The systems are combined using RWTH’s system combination approach. The final submission shows an improvement of 1.0 BLEU compared to the best single system on newstest2016.

Alignment-Based Neural Machine Translation.

Neural machine translation (NMT) has emerged recently as a promising statistical machine translation approach. In NMT, neural networks (NN) are directly used to produce translations, without relying on a pre-existing translation framework. In this work, we take a step towards bridging the gap between conventional word alignment models and NMT. We follow the hidden Markov model (HMM) approach that separates the alignment and lexical models. We propose a neural alignment model and combine it with a lexical neural model in a loglinear framework. The models are used in a standalone word-based decoder that explicitly hypothesizes alignments during search. We demonstrate that our system outperforms attention-based NMT on two tasks: IWSLT 2013 German→English and BOLT Chinese→English. We also show promising results for re-aligning the training data using neural models.

Local System Voting Feature for Machine Translation System Combination

In this paper, we enhance the traditional confusion network system combination approach with an additional model trained by a neural network. This work is motivated by the fact that the commonly used binary system voting models only assign each input system a global weight which is responsible for the global impact of each input system on all translations. This prevents individual systems with low system weights from having influence on the system combination output, although in some situations this could be helpful. Further, words which have only been seen by one or few systems rarely have a chance of being present in the combined output. We train a local system voting model by a neural network which is based on the words themselves and the combinatorial occurrences of the different system outputs. This gives system combination the option to prefer other systems at different word positions even for the same sentence.

The RWTH Aachen German-English Machine Translation System for WMT 2014

This paper describes the statistical machine translation system developed at RWTH Aachen University for the German!English translation task of the EMNLP 2015 Tenth Workshop on Statistical Machine Translation (WMT 2015). A phrase-based machine translation system was applied and augmented with hierarchical phrase reordering and word class language models. Further, we ran discriminative maximum expected BLEU training for our system. In addition, we utilized multiple feed-forward neural network language and translation models and a recurrent neural network language model for reranking.

Empirical Investigation of Optimization Algorithms in Neural Machine Translation

Abstract Training neural networks is a non-convex and a high-dimensional optimization problem. In this paper, we provide a comparative study of the most popular stochastic optimization techniques used to train neural networks. We evaluate the methods in terms of convergence speed, translation quality, and training stability. In addition, we investigate combinations that seek to improve optimization in terms of these aspects. We train state-of-the-art attention-based models and apply them to perform neural machine translation. We demonstrate our results on two tasks: WMT 2016 En→Ro and WMT 2015 De→En.