Cette recherche s'applique uniquement aux ressources en bibliothèque.
138 résultats
Trier par:
Ajouter à la liste:
Étendre à toutes les références (sans texte intégral)
    • Plusieurs versions

    Machine translation for Arabic dialects (survey)

    Harrat, Salima, Meftouh, Karima, Smaili, Kamel
    Information Processing and Management, March 2019, Vol.56(2), pp.262-273 [Revue évaluée par les pairs]

    • Livre
    Sélectionner

    Islam : méconnaissance et malentendu : essai

    Smaïli, Kamel
    Paris : Les impliqués
    2017
    Recherche de la disponibilité
    Plus…
    Chargement
    Erreur de chargement
    Titre: Islam : méconnaissance et malentendu : essai / Kamel Smaïli
    Auteur: Smaïli, Kamel
    Editeur: Paris : Les impliqués
    Date: 2017
    Collation: 1 vol. (129 p.) ; 22 cm
    Sujet RERO: Islam
    Identifiant: 9782343124162 13 EUR (ISBN); http://catalogue.bnf.fr/ark:/12148/cb45323393g (URN)
    No RERO: R008693283
    Permalien:
    http://data.rero.ch/01-R008693283/html?view=FR_V1

    • Plusieurs versions

    Alignment of comparable documents: comparison of similarity measures on French-English-Arabic data

    Langlois, David, Saad, Motaz, Smaïli, Kamel
    Natural Language Engineering, 19 June 2018, Vol.24(5), pp.677-694 [Revue évaluée par les pairs]

    • Article
    Sélectionner

    Statistical Machine Translation from Arab Vocal Improvisation to Instrumental Melodic Accompaniment

    Al-Ghawanmeh, Fadi, Smaïli, Kamel
    Journal of International Science and General Applications, 2018, Vol.1(1), pp.11-17
    Hyper Article en Ligne (CCSd), Hyper Article en Ligne Open Access (CCSd)
    Disponible
    Plus…
    Titre: Statistical Machine Translation from Arab Vocal Improvisation to Instrumental Melodic Accompaniment
    Auteur: Al-Ghawanmeh, Fadi; Smaïli, Kamel
    Contributeur: Smaïli, Kamel (Editor)
    Sujet: Computer Science ; Computation and Language ; Computer Science
    Description: Vocal improvisation is an essential practice in Arab music. The interactivity between the singer and the instrumentalist(s) is a main featureof thisdeep-rooted musical form. As part of the inter-activity, the instrumentalist recapitulates, or translates, each vocal sentence upon its completion. In this paper, we present our own parallel corpus of instrumentally accompanied Arab vocal improvisation. The initial size of the corpus is 2779 parallel sentences. We discuss the process of building this corpus as well as the choice of data representation. We also present some statistics about the corpus. Then we present initial experiments on applying statistical machine translation to propose an automatic instrumental accompanimenttoArabvocalimprovisation. Theresults with this small corpus, in comparison to classical machine translation of natural languages, are very promising: a BLEU of 24.62 from Vocal to instrumental and 24.07 from instrumental to vocal.
    Fait partie de: Journal of International Science and General Applications, 2018, Vol.1(1), pp.11-17
    Identifiant: 2351-8715 (ISSN)

    • Article
    Sélectionner

    A Translation Evaluation Function based on Neural Network

    Douib, Ameur, Langlois, David, Smaili, Kamel
    Schedae Informaticae, 24 March 2017, Vol.25, pp.139-151 [Revue évaluée par les pairs]
    Hyper Article en Ligne (CCSd), Hyper Article en Ligne Open Access (CCSd)
    Disponible
    Plus…
    Titre: A Translation Evaluation Function based on Neural Network
    Auteur: Douib, Ameur; Langlois, David; Smaili, Kamel
    Contributeur: Smaïli, Kamel (Editor)
    Sujet: Computer Science ; Computation and Language ; Statistical Machine Translation ; Genetic Algorithm ; Quality Esti- Mation ; Neural Network ; Computer Science
    Description: In this paper, we study the feasibility of using a neural network to learn a fitness function for a machine translation system based on a genetic algorithm termed GAMaT. The neural network is learned on features extracted from pairs of source sentences and their translations. The fitness function is trained in order to estimate the BLEU of a translation as precisely as possible. The estimator has been trained on a corpus of more than 1.3 million data. The performance is very promising: the difference between the real BLEU and the one given by the estimator is equal to 0.12 in terms of Mean Absolute Error.
    Fait partie de: Schedae Informaticae, 24 March 2017, Vol.25, pp.139-151
    Identifiant: 10.4467/20838476SI.16.011.6192 (DOI)

    • Article
    Sélectionner

    Using Word Embeddings to Retrieve Semantically Similar Questions in Community Question Answering

    Othman, Nouha, Faiz, Rim, Smaïli, Kamel
    Journal of International Science and General Applications, 01 March 2018, Vol.1(1)
    Hyper Article en Ligne (CCSd), Hyper Article en Ligne Open Access (CCSd)
    Disponible
    Plus…
    Titre: Using Word Embeddings to Retrieve Semantically Similar Questions in Community Question Answering
    Auteur: Othman, Nouha; Faiz, Rim; Smaïli, Kamel
    Contributeur: Smaïli, Kamel (Editor)
    Sujet: Computer Science ; Computation and Language ; Computer Science
    Description: This paper focuses on question retrieval which is a crucial and tricky task in Community Question Answering (cQA). Question retrieval aims at finding historical questions that are semantically equivalent to the queried ones, assuming that the answers to the similar questions should also answer the new ones. The major challenges are the lexical gap problem as well as the verboseness in natural language. Most existing methods measure the similarity between questions based on the bag-of-words (BOWs) representation capturing no semantics between words. In this paper, we rely on word embeddings and TF-IDF for a meaningful vector representation of the questions. The similarity between questions is measured using cosine similarity based on their vector-based word representations. Experiments carried out on a real world data set from Yahoo! Answers show that our method is competetive.
    Fait partie de: Journal of International Science and General Applications, 01 March 2018, Vol.1(1)
    Identifiant: 2351-8715 (ISSN)

    • Article
    Sélectionner

    Maghrebi Arabic dialect processing: an overview

    Harrat, Salima, Meftouh, Karima, Smaïli, Kamel
    Journal of International Science and General Applications, 01 March 2018, Vol.1
    Hyper Article en Ligne (CCSd), Hyper Article en Ligne Open Access (CCSd)
    Disponible
    Plus…
    Titre: Maghrebi Arabic dialect processing: an overview
    Auteur: Harrat, Salima; Meftouh, Karima; Smaïli, Kamel
    Contributeur: Smaïli, Kamel (Editor)
    Sujet: Computer Science ; Computation and Language ; Computer Science
    Description: Natural Language Processing for Arabic dialects has grown widely these last years. Indeed, several works were proposed dealing with all aspects of Natural Language Processing. However, some AD varieties have received more attention and have a growing collection of resources. Others varieties, such as Maghrebi, still lag behind in that respect. Maghrebi Arabic is the family of Arabic dialects spoken in the Maghreb region (principally Algeria, Tunisia and Morocco). In this work we are interested in these three languages. This paper presents a review of natural language processing for Maghrebi Arabic dialects.
    Fait partie de: Journal of International Science and General Applications, 01 March 2018, Vol.1
    Identifiant: 2351-8715 (ISSN)

    • Article
    Sélectionner

    Phrase-Based Language Model in Statistical Machine Translation

    Ben Romdhane, Achraf, Jamoussi, Salma, Ben Hamadou, Abdelmajid, Smaïli, Kamel
    International Journal of Computational Linguistics and Applications, 08 December 2016
    Hyper Article en Ligne (CCSd), Hyper Article en Ligne Open Access (CCSd)
    Disponible
    Plus…
    Titre: Phrase-Based Language Model in Statistical Machine Translation
    Auteur: Ben Romdhane, Achraf; Jamoussi, Salma; Ben Hamadou, Abdelmajid; Smaïli, Kamel
    Contributeur: Smaïli, Kamel (Editor)
    Sujet: Computer Science ; Computation and Language ; Machine Translation ; Phrases ; Phrase Based Language Model ; Decoding Optimization ; Computer Science
    Description: As one of the most important modules in statistical machine translation (SMT), language model measures whether one translation hypothesis is more grammatically correct than other hypotheses. Currently the state-of-the-art SMT systems use standard word n-gram models, whereas the translation model is phrase-based. In this paper, the idea is to use a phrase-based language model. For that, target portion of the translation table are retrieved and used to rewrite the training corpus and to calculate a phrase n-gram language model. In this work, weperform experiments with two language models word-based (WBLM) and phrase-based (PBLM). The different SMT are trained with threeoptimization algorithms MERT, MIRA and PRO. Thus, the PBLM systems are compared to the baseline system in terms of BLUE and TER.The experimental results show that the use of a phrase-based language model in SMT can improve results and is especially able to reduce theerror rate.
    Fait partie de: International Journal of Computational Linguistics and Applications, 08 December 2016
    Identifiant: 0976-0962 (ISSN)

    • Article
    Sélectionner

    Modeling Arabic Language using statistical methods

    Meftouh, Karima, Laskri, Med Tayeb Tayeb, Smaïli, Kamel
    Arabian Journal for Science and Engineering, 01 December 2010, Vol.35(2C), pp.69-82 [Revue évaluée par les pairs]
    Hyper Article en Ligne (CCSd), Hyper Article en Ligne Open Access (CCSd)
    Disponible
    Plus…
    Titre: Modeling Arabic Language using statistical methods
    Auteur: Meftouh, Karima; Laskri, Med Tayeb Tayeb; Smaïli, Kamel
    Contributeur: Smaïli, Kamel (Editor)
    Sujet: Computer Science ; Computation and Language ; Modèle de Langage ; Morphèmes ; Perplexité ; Lissage ; Modèle Distant ; Engineering ; Computer Science
    Description: In this paper we propose to investigate statistical language models for Arabic. First, several experiments using different smoothing techniques are carried out on a small corpus extracted from a daily newspaper. The sparseness of the data leads us to investigate other solutions without increasing the size of the corpus. A word segmentation technique has been employed in order to increase the statistical viability of the corpus. An n-morpheme model has been developed which leads to a better performance in terms of normalized perplexity. The second experiment concerns the study of the behaviour of statistical models based on different kinds of corpora. The introduction of distant n-gram improves the baseline model. Finally we propose a comparative study of statistical language models for Arabic and several foreign languages. The objective of this study is to understand how to better model each of this languages. For foreign languages, trigram models are most appropriate whatever...
    Fait partie de: Arabian Journal for Science and Engineering, 01 December 2010, Vol.35(2C), pp.69-82
    Identifiant: 1319-8025 (ISSN); 2191-4281 (E-ISSN)

    • Plusieurs versions

    Extracting Comparable Articles from Wikipedia and Measuring their Comparabilities

    Saad, Motaz, Langlois, David, Smaïli, Kamel
    Procedia - Social and Behavioral Sciences, 25 October 2013, Vol.95, pp.40-47 [Revue évaluée par les pairs]