Making the distinction between expert and non expert health documents can help users to select the information which is more suitable for them, according to whether they are familiar or not with medical terminology. This issue is particularly important for the information retrieval area. In our work we address this purpose through stylistic corpus analysis and the application of machine learnin...

In this study we present various techniques to evaluate the pronunciation of students of a foreign language without any knowledge of the uttered text. Previous attempts have shown that it is feasible to evaluate the pronunciation of a non-native speaker by having implicit or explicit knowledge of the uttered text, provided that enough utterances are available. Our approach is to use characteris...

Cross-lingual relevance modelling (CLRLM) is a state-of-the-art technique for cross-lingual information retrieval (CLIR) which integrates query term disambiguation and expansion in a unified framework, to directly estimate a model of relevant documents in the target language starting with a query in the source language. However, CLRLM involves integrating a translation model either on the docum...

The present paper describes an approach to adapting a parser to a new language. Presumably the target language is much poorer in linguistic resources than the source language. The technique has been tested on two European languages due to test data availability; however, it is easily applicable to any pair of sufficiently related languages, including some of the Indic language group. Our adapta...

We present a language independent, unsupervised approach for transforming word embeddings from source language to target language using a transformation matrix. Our model handles the problem of data scarcity which is faced by many languages in the world and yields improved word embeddings for words in the target language by relying on transformed embeddings of words of the source language. We i...

Statistical machine translation is often faced with the problem of having insufficient training data for many language pairs. In this thesis, several methods have been proposed to leverage other sources to enhance the quality of machine translation systems. Particularly, we propose approaches suitable in these four scenarios: 1. when an additional parallel corpus between the source and the targ...

The baseline approach in building phonotactic language recognition systems is to characterize each language by a single phonotactic model generated from all the available languagespecific training data. When several data sources are available for a given target language, system performance can be improved using language source-dependent phonotactic models. In this case, the common practice is t...

While neural machine translation (NMT) has made remarkable progress in translating a handful of resource-rich language pairs recently, parallel corpora are not always readily available for most language pairs. To deal with this problem, we propose an approach to zero-resource NMT via maximum expected likelihood estimation. The basic idea is to maximize the expectation with respect to a pivot-to...

A controlled language is a subset of a natural language with artificially restricted vocabulary, grammar, and style. Texts written in a controlled language are usually less complex and less ambiguous than those written in an uncontrolled language. The use of a controlled language therefore produces better results in machine translation. On the other hand, a controlled language reduces the power...