We construct a semiclassical Friedmann-Lemaître-Robertson-Walker (FLRW) cosmological model assuming a running cosmological constant (CC). It turns out that the CC becomes variable at arbitrarily low energies due to the remnant quantum effects of the heaviest particles, e.g. the Planck scale physics. These effects are universal in the sense that they lead to a low-energy structure common to a large class of high-energy theories. Remarkably, the uncertainty concerning the unknown high-energy dynamics is accumulated into a single parameter ν, such that the model has an essential predictive power. Future Type Ia supernovae experiments (like SNAP) can verify whether this framework is correct. For the flat FLRW case and a moderate value ν ∼ 10 −2 , we predict an increase of 10 − 20% in the value of Ω Λ at redshifts z = 1 − 1.5 perfectly reachable by SNAP.

Within the Quantum Field Theory context the idea of a "cosmological constant" (CC) evolving with time looks quite natural as it just reflects the change of the vacuum energy with the typical energy of the universe. In the particular frame of Ref.[31], a "running CC" at low energies may arise from generic quantum effects near the Planck scale, M P , provided there is a smooth decoupling of all massive particles below M P . In this work we further develop the cosmological consequences of a "running CC" by addressing the accelerated evolution of the universe within that model. The rate of change of the CC stays slow, without fine-tuning, and is comparable to H 2 M 2 P . It can be described by a single parameter, ν, that can be determined from already planned experiments using SNe Ia at high z. The range of allowed values for ν follows mainly from nucleosynthesis restrictions. Present samples of SNe Ia can not yet distinguish between a "constant" CC or a "running" one. The numerical simulations presented in this work show that SNAP can probe the predicted variation of the CC either ruling out this idea or confirming the evolution hereafter expected.

End-to-end neural machine translation has overtaken statistical machine translation in terms of translation quality for some language pairs, specially those with large amounts of parallel data. Besides this palpable improvement, neural networks provide several new properties. A single system can be trained to translate between many languages at almost no additional cost other than training time. Furthermore, internal representations learned by the network serve as a new semantic representation of words or sentences which, unlike standard word embeddings, are learned in an essentially bilingual or even multilingual context. In view of these properties, the contribution of the present work is two-fold. First, we systematically study the NMT context vectors, i.e. output of the encoder, and their power as an interlingua representation of a sentence. We assess their quality and effectiveness by measuring similarities across translations, as well as semantically related and semantically unrelated sentence pairs. Second, as extrinsic evaluation of the first point, we identify parallel sentences in comparable corpora, obtaining an F 1 = 98.2% on data from a shared task when using only NMT context vectors. Using context vectors jointly with similarity measures F 1 reaches 98.9%.

We present a simple new method where an emergent NMT system is used for simultaneously selecting training data and learning internal NMT representations. This is done in a self-supervised way without parallel data, in such a way that both tasks enhance each other during training. The method is language independent, introduces no additional hyper-parameters, and achieves BLEU scores of 29.21 (en2f r) and 27.36 (f r2en) on new-stest2014 using English and French Wikipedia data for training.

Abstract. Automatic Speech Recognition has reached almost human performance in some controlled scenarios. However, recognition of impaired speech is a difficult task for two main reasons: data is (i) scarce and (ii) heterogeneous. In this work we train different architectures on a database of dysarthric speech. A comparison between architectures shows that, even with a small database, hybrid DNN-HMM models outperform classical GMM-HMM according to word error rate measures. A DNN is able to improve the recognition word error rate a 13% for subjects with dysarthria with respect to the best classical architecture. This improvement is higher than the one given by other deep neural networks such as CNNs, TDNNs and LSTMs. All the experiments have been done with the Kaldi toolkit for speech recognition for which we have adapted several recipes to deal with dysarthric speech and work on the TORGO database. These recipes are publicly available.

Multiple approaches to grab comparable data from the Web have been developed up to date. Nevertheless, coming out with a high-quality comparable corpus of a specific topic is not straightforward. We present a model for the automatic extraction of comparable texts in multiple languages and on specific topics from Wikipedia. In order to prove the value of the model, we automatically extract parallel sentences from the comparable collections and use them to train statistical machine translation engines for specific domains. Our experiments on the EnglishSpanish pair in the domains of Computer Science, Science, and Sports show that our in-domain translator performs significantly better than a generic one when translating in-domain Wikipedia articles. Moreover, we show that these corpora can help when translating out-of-domain texts.

Recent studies use a combination of lexical and syntactic features to show that footprints of the source language remain visible in translations, to the extent that it is possible to predict the original source language from the translation. In this paper, we focus on embedding-based semantic spaces, exploiting departures from isomorphism between spaces built from original target language and translations into this target language to predict relations between languages in an unsupervised way. We use different views of the data -words, parts of speech, semantic tags and synsets -to track translationese. Our analysis shows that (i) semantic distances between original target language and translations into this target language can be detected using the notion of isomorphism, (ii) language family ties with characteristics similar to linguistically motivated phylogenetic trees can be inferred from the distances and (iii) with delexicalised embeddings exhibiting source-language interference most significantly, other levels of abstraction display the same tendency, indicating the lexicalised results to be not "just" due to possible topic differences between original and translated texts. To the best of our knowledge, this is the first time departures from isomorphism between embedding spaces are used to track translationese.

This article presents a hybrid architecture which combines rule-based machine translation (RBMT) with phrase-based statistical machine translation (SMT). The hybrid translation system is guided by the rule-based engine. Before the transfer step, a varied set of partial candidate translations is calculated with the SMT system and used to enrich the tree-based representation with more translation alternatives. The final translation is constructed by choosing the most probable combination among the available fragments using monotone statistical decoding following the order provided by the rule-based system. We apply the hybrid model to a pair of distantly related languages, Spanish and Basque, and perform extensive experimentation on two different corpora. According to our empirical evaluation, the hybrid approach outperforms the best individual system across a varied set of automatic translation evaluation metrics. Following some output analysis to better understand the behaviour of the hybrid system, we explore the possibility of adding alternative parse trees and extra features to the hybrid decoder. Finally, we present a twofold manual evaluation of the translation systems studied in this paper, consisting of (i) a pairwise output comparison and (ii) a individual task-oriented evaluation using HTER. Interestingly, the manual evaluation shows some contradictory results with respect to the automatic evaluation; humans tend to prefer the translations from the RBMT system over the statistical and hybrid translations.Peer ReviewedPostprint (author’s final draft