For the plant task of the LifeCLEF challenge, we adopted the reference Bag-of-Word framework (BoW) with local soft assignment. The points of interests (POI) are both detected and described with the SIFT and OpponentColor SIFT. Parameters of the bag of word are optimized through cross-validation and we present the results of different experimentations. A Support Vector Machine is trained with di...

Performance of word sense disambiguation (WSD) is one the challenging tasks in area natural language processing (NLP). Generation annotated corpus for multilingual out reach most languages even if resources are available. In this paper we propose an unsupervised method using and embedding or improving performance these systems untagged. Corpora create two bags namely ontological bag wiki to gen...

This master’s theses addressed two research issues in order to investigate and to propose effective solutions for image retrieval on mobile devices: 1) low-cost representation for mobile image search and 2) spatial visual feature extraction. First, we have tested twenty mid-level representations of binary descriptors, ten color descriptors, five texture descriptors and two shape descriptors in ...

In this paper, we describe an approach to the automatic plant identification task of the LifeCLEF 2014 lab. The image descriptors for all submitted runs were obtained using the bag-of-visual-words method. For the leaf scans, we use multiscale triangular shape descriptor and for the other plant organs Opponent SIFT extracted around points of interest obtained using Harris-Laplace detector. We th...

This work explores the effect of text representation techniques on the overall performance of medical text classification. To accomplish this goal, we developed a text classification system that supports the very basic word representation (bag-of-words) and the more complex medical phrase representation (bag-of-phrases). We also combined word and phrase representations (hybrid) for further anal...

Vector-space models, from word embeddings to neural network parsers, have many advantages for NLP. But how to generalise from fixed-length word vectors to a vector space for arbitrary linguistic structures is still unclear. In this paper we propose bag-of-vector embeddings of arbitrary linguistic graphs. A bag-of-vector space is the minimal nonparametric extension of a vector space, allowing th...