Time filter

Source Type

Aliane H.,Research Center on Scientific and Technical Information | Guendouzi A.,University of Science and Technology Houari Boumediene | Mokrani A.,University of Science and Technology Houari Boumediene
International Conference Recent Advances in Natural Language Processing, RANLP | Year: 2013

We present in this paper an unsupervised approach to recognize events, time and place expressions in Arabic texts. Arabic is a resource -scarce language and we don't easily have at hand annotated corpora, lexicons and other needed NLP tools. We show in this work that we can recognize events, time and place expressions in Arabic texts without using a POS annotated corpus and without lexicon. We use an unsupervised segmentation algorithm then a minimalist set of rules allows us to get a partial POS annotation of our corpus. This partially annotated corpus will serve as a basis for the recognition process which implements a set of rules using specific linguistic markers to recognize events, and expressions of time and place. Source

Bessai-Mechmache F.Z.,Research Center on Scientific and Technical Information | Alimazighi Z.,University of Science and Technology Houari Boumediene
International Journal of Intelligent Information and Database Systems | Year: 2012

In this paper, we are interested in content-oriented XML information retrieval which aims to retrieve not a set of relevant documents but a number of elements (parts of document) relevant to a query. Our goal is to revisit the granularity of the unit to be returned. More precisely, instead of returning the whole document or a list of disjoint elements of a document, as it is usually done in the most XML information retrieval systems, we attempt to build the best elements aggregation (set of non-redundant elements) which is likely to be relevant to a query composed of key words. Our approach is based on possibilistic networks. The network structure provides a natural representation of links between a document, its elements and its content, and allows an automatic selection of a combination of independent elements (i.e., set of non-redundant elements from different parts of the document tree) that better answers the user's query. Experiments carried out on a sub-collection of INEX INitiative for the evaluation of XML (INEX) retrieval, showed the effectiveness of the approach. Copyright © 2012 Inderscience Enterprises Ltd. Source

Bouchama S.,Research Center on Scientific and Technical Information | Aliane H.,Research Center on Scientific and Technical Information | Hamami L.,Polytechnic School of Algiers
2013 International Conference on Information Science and Applications, ICISA 2013 | Year: 2013

Very few reversible data hiding methods are proposed for compressed video and particularly for the H.264/AVC video codec, despite the importance of both of the watermarking reversibility criterion and the codec. The reversible watermarking techniques of images, when applied to the compressed video, can affect particularly the video quality and bitrate. Thus, to make these techniques applicable, the embedding capacity is usually reduced. Therefore an adaptation is necessary to improve the tradeoff between the embedding capacity, the visual quality and the bitrate of the watermarked video. In this paper, we investigate the possibility to introduce the DCT based reversible data hiding method, proposed initially for compressed images, to H.264/AVC codec. The embedding is applied during the encoding process, in the quantized DCT coefficients of I and P frames. To enhance the embedding capacity a mapping rule is used to embed three bits in one coefficient. Results show that exploiting the P frames improves considerably the video quality and the embedding capacity. © 2013 IEEE. Source

Maredj A.-E.,Research Center on Scientific and Technical Information | Tonkin N.,Research Center on Scientific and Technical Information
Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015 | Year: 2015

We propose an approach for the dynamic adaptation of multimedia documents modeled by an over-constrained constraint satisfaction problem (OCSP). In addition the solutions that it provides for the problem of determining the relations that do not comply with the user profile and the problem of the combinatorial explosion when searching for alternative relations, it insures a certain quality of service to the presentation of the adapted document: (i) If the required constraints are not satisfied, no document is generated, unlike other approaches that generates even if the presentation of the adapted document is completely different from the initial one, (ii) The definition of the constraints hierarchy (strong constraints and medium constraints) maintains as much as possible of the initial document relations in the adapted one. As result, the adapted presentations are consistent and close to those of the initial ones. © 2015 IEEE. Source

Aliane H.,Research Center on Scientific and Technical Information | Alimazighi Z.,University for Information Science and Technology
International Journal of Computer Applications in Technology | Year: 2011

We present a new approach to discover Arabic language structures from electronic texts. The method is based on a distributional analysis inspired from Arabic Grammatical Tradition (AGT) and Harris, and uses a minimum knowledge about the Arabic language. The idea underlying this research is that in the absence of a formal model of Arabic language and freely usable Natural Language Processing (NLP) tools for this language, what we can learn about the structures of this language only by a formal analysis of raw corpora written in it. By the word 'formal' we mean, here, that the analysis is based only on the form of the written texts and uses only a minimum knowledge about the language. This knowledge consists in some minimal hypothesis inspired from AGT and that never refers to the meaning of words, utterances and texts. On the contrary, we do not yet know these structures, but we want to discover them formally by automatic algorithms. © 2011 Inderscience Enterprises Ltd. Source

Discover hidden collaborations