We present a dialectal Egyptian Arabic to English statistical machine translation system that leverages dialectal to Modern Standard Arabic (MSA) adaptation. In contrast to previous work, we first narrow down the gap between Egyptian and MSA by applying an automatic characterlevel transformational model that changes Egyptian to EG′, which looks similar to MSA. The transformations include morpho...

JANUS is a multilingual speech-to-speech translation system, which has been designed to translate spontaneous spoken language in a limited domain. In this paper, we describe our recent preliminary eeorts to expand the domain of coverage of the system from the rather limited Appointment Scheduling domain, to the much richer Travel Planning domain. We compare the two domains in terms of out-of-vo...

JANUS is a multi-lingual speech-to-speech translation system, which has been designed to translate spontaneous spoken language in a limited domain. In this paper, we describe our recent preliminary e orts to expand the domain of coverage of the system from the rather limited Appointment Scheduling domain, to the much richer Travel Planning domain. We compare the two domains in terms of out-of-v...

Word embeddings – distributed representations of words – in deep learning are beneficial for many tasks in NLP. However, different embedding sets vary greatly in quality and characteristics of the captured information. Instead of relying on a more advanced algorithm for embedding learning, this paper proposes an ensemble approach of combining different public embedding sets with the aim of lear...

This paper describes the development of a specialized lexical resource for a specialized domain, namely medicine. Based on the observation of a large collection of terms, we highlight the specificities that such a lexicon should take into account, and we show that general resources lack a large part of the words needed to process specialized language. We describe an experiment to feed semi-auto...

Recognizing similar or close meaning on different surface form is a common challenge in various Natural Language Processing and Information Access applications. However, we identified multiple limitations in existing resources that can be used for solving the vocabulary mismatch problem. To this end, we will propose the Diversifiable Bootstrapping algorithm that can learn paraphrase patterns wi...

As language learners scale up in terms of speaking proficiency, they expand the volume of expressions in the target language that they can use in a robust fashion, combining vocabulary and syntactic structures into novel constructions and transferring them to new contexts. In the ISLET Project, sponsored by the Office of Naval Research (ONR), we have developed a strategy for allowing a dialog-r...

Designing appropriate materials and activities to enhance vocabulary learning is one of the primary goals of language courses. Among the claims about efficient pedagogical tasks is the Involvement Load Hypothesis (Laufer & Hulstijn, 2001) according to which vocabulary development is contingent on the amount of cognitive process a task involves. Building on the previous research on this hypothes...

abstractthis study investigated the effect of digital games on vocabulary acquisition of low-proficiency iranian male and female efl learners. in order to select homogeneous learners in terms of their english language proficiency, the standard nelson proficiency test was administered, and based on the obtained results, 60 low-proficiency efl learners were selected (31 females and 29 males). the...