The task of native language (L1) identification suffers from a relative paucity of useful training corpora, and standard within-corpus evaluation is often problematic due to topic bias. In this paper, we introduce a method for L1 identification in second language (L2) texts that relies only on much more plentiful L1 data, rather than the L2 texts that are traditionally used for training. In par...

Abstract We have built a corpus containing texts in 106 languages from texts available on the Internet and on Wikipedia. The W2C Web Corpus contains 54.7 GB of text and the W2C Wiki Corpus contains 8.5 GB of text. The W2C Web Corpus contains more than 100 MB of text available for 75 languages. At least 10 MB of text is available for 100 languages. These corpora are a unique data source for ling...

Particle Swarm Optimization (PSO) is a metaheuristic optimization algorithm that owes much of its allure to its simplicity and its high effectiveness in solving sophisticated optimization problems. However, since the performance of the standard PSO is prone to being trapped in local extrema, abundant variants of PSO have been proposed by far. For instance, Fuzzy Adaptive PSO (FAPSO) algorithms ...

In this work we tried to solve some non-linear problems of analytic photogrammetry. These problems are also widely flowed into the digital photogrammetry. The model formation considering the solution of the Relative Orientation, and the object reconstruction considering the solution of the Absolute Orientation have non-linear functional models. These models need an exhaustive research of the pr...

Instructional texts consist of sequences of instructions designed in order to reach an objective. The user must follow step by step the instructions in order to reach the results expected. In this short paper, we explore the different facets of natural argumentation used in such texts. Our study is based on an extensive corpus study, and within a language generation perspective. 1 General typol...

We present REDEN, a tool for graph-based Named Entity Linking that allows for the disambiguation of entities using domainspecific Linked Data sources and different configurations (e.g. context size). It takes TEI-annotated texts as input and outputs them enriched with external references (URIs). The possibility of customizing indexes built from various knowledge sources by defining temporal and...

We explore the task of automatic classification of texts by the emotions expressed. Our novel method arranges neutrality, polarity and emotions hierarchically. We test the method on two datasets and show that it outperforms the corresponding “flat” approach, which does not take into account the hierarchical information. The highly imbalanced structure of most of the datasets in this area, parti...

Automated discovery and extraction of biological relations from online documents, particularly MEDLINE texts, has become essential and urgent because such literature data are accumulated in a tremendous growth. We present here an ontology-based framework of biological relation extraction system. This framework is unified and able to extract several kinds of relations such as gene-disease, gene-...

The research area of information extraction (IE) aims to extract relevant structured information from natural language texts. In addition to the named-entity recognition (NER) task, the identification and classification of relations among entities, namely, the so-called relation extraction (RE) task, is particularly important for many real-world applications. Given the sentence in Figure 1, a R...

Background Purposeful intake of ample dietary protein remains controversial, as illustrated by uncertain and/or dissuasive material in introductory dietetics texts and statements by professional organizations (Lowery L and Huffman J, Dietary Protein in Sport: Still Controversial, ASEP National Meeting, 2008). Common health concerns include undue "stress" on renal function, bone loss, and delete...