The present article provides a comprehensive review of the work carried out on developing PRESEMT, a hybrid language-independent machine translation (MT) methodology. This methodology has been designed to facilitate rapid creation of MT systems for unconstrained language pairs, setting the lowest possible requirements on specialised resources and tools. Given the limited availability of resources for many languages, only a very small bilingual corpus is required, while language modelling is performed by sampling a large target language (TL) monolingual corpus. The article summarises implementation decisions, using the Greek-English language pair as a test case. Evaluation results are reported, for both objective and subjective metrics. Finally, main error sources are identified and directions are described to improve this hybrid MT methodology. 1 Introduction and

Distributed representations of words have proven extremely useful in numerous natural language processing tasks. Their appeal is that they can help alleviate data sparsity problems common to supervised learning. Methods for inducing these representations require only unlabeled language data, which are plentiful for many natural languages. In this work, we induce distributed representations for a pair of languages jointly. We treat it as a multitask learning problem where each task corresponds to a single word, and task relatedness is derived from co-occurrence statistics in bilingual parallel data. These representations can be used for a number of crosslingual learning tasks, where a learner can be trained on annotations present in one language and applied to test data in another. We show that our representations are informative by using them for crosslingual document classification, where classifiers trained on these representations substantially outperform strong baselines (e.g. machine translation) when applied to a new language.

Prior research into learning translations from source and target language monolingual texts has treated the task as an unsupervised learning problem. Although many techniques take advantage of a seed bilingual lexicon, this work is the first to use that data for supervised learning to combine a diverse set of signals derived from a pair of monolingual corpora into a single discriminative model. Even in a low resource machine translation setting, where induced translations have the potential to improve performance substantially, it is reasonable to assume access to some amount of data to perform this kind of optimization. Our work shows that only a few hundred translation pairs are needed to achieve strong performance on the bilingual lexicon induction task, and our approach yields an average relative gain in accuracy of nearly 50 % over an unsupervised baseline. Large gains in accuracy hold for all 22 languages (low and high resource) that we investigate. 1

Statistical machine translation (SMT) performance suffers when models are trained on only small amounts of parallel data. The learned models typically have both low accuracy (incorrect translations and feature scores) and low coverage (high out-of-vocabulary rates). In this work, we use an additional data resource, comparable corpora, to improve both. Beginning with a small bitext and corresponding phrase-based SMT model, we improve coverage by using bilingual lexicon induction techniques to learn new translations from comparable corpora. Then, we supplement the model’s feature space with translation scores estimated over comparable corpora in order to improve accuracy. We observe improvements between 0.5 and 1.7 BLEU translating Tamil, Telugu,

This second edition of the Workshop on Hybrid Approaches to Translation (HyTra) is co-located with the 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013) in Sofia. It further progresses on the findings of the first edition which was held as a joint 2-day event together with the Workshop on Exploiting Synergies between Information Retrieval and Machine Translation (ESIRMT) at the 13th Conference of the European Chapter of the Association for Computational Linguistics (EACL

Distributed representations of words have proven extremely useful in numerous natural language processing tasks. Their appeal is that they can help alleviate data sparsity problems common to supervised learning. Methods for inducing these representations require only unlabeled language data, which are plentiful for many natural languages. In this work, we induce distributed representations for a pair of languages jointly. We treat it as a multitask learning problem where each task corresponds to a single word, and task relatedness is derived from co-occurrence statistics in bilingual parallel data. These representations can be used for a number of crosslingual learning tasks, where a learner can be trained on annotations present in one language and applied to test data in another. We show that our representations are informative by using them for crosslingual document classification, where classifiers trained on these representations substantially outperform strong baselines (e.g. machine translation) when applied to a new language.