Lahbib Zenkouar

POS tagging in Amazighe using support vector machines and conditional random fields

The aim of this paper is to present the first Amazighe POS tagger. Very few linguistic resources have been developed so far for Amazighe and we believe that the development of a POS tagger tool is the first step needed for automatic text processing. The used data have been manually collected and annotated. We have used state-of-art supervised machine learning approaches to build our POS-tagging models. The obtained accuracy achieved 92.58% and we have used the 10-fold technique to further validate our results.

Using confidence and informativeness criteria to improve POS-tagging in amazigh

Amazigh is used by tens of millions of people mainly for oral communication. However, and like all the newly investigated languages in natural language processing, it is resource-scarce. The main aim of this paper is to present our POS taggers results based on two state of the art sequence labeling techniques, namely Conditional Random Fields and Support Vector Machines, by making use of a small manually annotated corpus of only 20k tokens. Since creating labeled data is very time-consuming task while obtaining unlabeled data is less so, we have decided to gather a set of unlabeled data of Amazigh language that we have preprocessed and tokenized. The paper is also meant to address using semi-supervised techniques to improve POS tagging accuracy. An adapted self training algorithm, combining confidence measure with a function of Out Of Vocabulary words to select data for self training, has been used. Using this language independent method, we have managed to obtain encouraging results.

The development of a fine grained class set for Amazigh POS tagging

Like most of the languages which have only recently started being investigated for the Natural Language Processing (NLP) tasks, Amazigh lacks annotated corpora and tools and still suffers from the scarcity of linguistic tools and resources. The main aim of this paper is to present a tokenizer tool and a new part-of-speech (POS) tagger based on a new Amazigh tag set (AMTS) composed of 28 tag. In line with our goal we have trained two sequence classification models using Support Vector Machines (SVMs) and Conditional Random Fields (CRFs) to build a toknizer and a POS tagger for the Amazigh language. We have used the 10-fold technique to evaluate and validate our approach. We report that POS tagging results using SVMs and CRFs are very comparable. Across the board, CRFs outperformed SVMs on the fold level (91.18% vs. 90.75%) and CRFs outperformed SVMs on the 10 folds average level (87.95% vs. 87.11%). Regarding tokenization task, SVMs outperformed CRFs on the fold level (99.97% vs. 99.85%) and on the 10 folds average level (99.95% vs. 99.89%).

Measure of the temperature-depth profile by an S band radiometric receiver for biomedical applications

The authors present a method for measuring the temperature-depth profile in a lossy material by applying Kalman algorithm to radiometric signals. The method employs a correlation microwave radiometer. It uses both short-range weighting functions and the delay times of the correlator. An experimental verification of this new thermal inversion approach is presented. The thermal noise is received in the microwave domain, by a S band radiometer by using an automatic experimental bench. A feature of this method is that it can be used in biomedical applications.RésuméLes auteurs présentent une méthode de mesure de la température en profondeur dans un milieu dissipatif par application de l’algorithme de Kalman aux signaux radiométriques. Cette méthode emploie un radiomètre micro-onde à corrélation. Elle utilise des fonctions de couplage qui caractérisent le couplage entre un milieu dissipatif et une antenne, et le temps de retard du corrélateur. Une vérification expérimentale de cette nouvelle approche d’inversion thermique est présentée. Le signal de bruit thermique est traité à l’aide d’un radiomètre à bande S, en utilisant un banc expérimental automatisé. Cette méthode est destinée, en particulier, à des applications biomédicales.

Build a Morphosyntaxically Annotated Amazigh Corpus

Language resources are important for those working on computational methods to analyze and study languages. These resources are needed to help advancing the research in fields such as natural language processing, machine learning, information retrieval and text analysis in general. We describe the creation of morphosyntactically annotated corpus for Amazigh language that currently lacks them. We illustrate our approach for creating this corpus, that is more expensive but of high quality, using crowdsourcing and manual effort with appropriately skilled human participants. Qualitative and quantitative evaluations of the resources are also presented.

Verbal morphological analyzer/generator for Amazigh moods based on XFST

This paper presents the first verbal morphological analyzer/generator for Amazigh moods using a system based on xeroxs finite-state transducer platform. In this context our system is based on two main components: a lexicon including 2443 attested verbs, and a set of rules covering the morphotactic and morphological phenomena observed in standard amazigh verbs. The choice of finite-state technology makes our system bidirectional (analyzer / generator) and able to cover all variations of amazigh mood, aspect, gender, and person, and to realize an important accuracy (system recognition) which has reached about 79.07%. This system is an added value for the implementation for other applications like spellchecking, machine translation, and computer aided language learning.

System of Analysis and Generation for Amazigh Nominal Morphology based on Xerox’s finite-state transducer

Abstract This paper presents the first system of analysis and generation for amazigh nominal morphology using a system based on xerox’s finite-state transducer platform. In this context our system is based on two main components: a lexicon including 2363 attested nouns, and a set of rules covering the morphotactic and morphological phenomena observed in standard amazigh texts. The choice of finite-state technology makes our system bidirectional (analyzer / generator) and able to cover all variations of amazigh noun (gender, number, state) and to realize an important accuracy (system recognition) which reaches about 77%. This system is an added value for the implementation for other applications like spellchecking, machine translation, and computer aided language learning.