This paper describes the development of a chunker for spoken data by supervised machine learning using the CRFs, based on a small reference corpus composed of two kinds of discourse: prepared monologue vs. spontaneous talk in interaction. The methodology considers the specific character of the spoken data. The machine learning uses the results of several available taggers, without correcting the results manually. Experiments show that the discourse type (monologue vs. free talk), the speech nature (spontaneous vs. prepared) and the corpus size can influence the results of the machine learning process and must be considered while interpreting the results.

Word embeddings are used with success for a variety of tasks involving lexical semantic similarities between individual words.Using unsupervised methods and just cosine similarity, encouraging results were obtained for analogical similarities.In this paper, we explore the potential of pre-trained word embeddings to identify generic types of semantic relations in an unsupervised experiment.We propose a new relational similarity measure based on the combination of word2vec's CBOW input and output vectors which outperforms alternative vector representations, when used for unsupervised clustering on SemEval 2010 Relation Classification data.

Like search engines, recommender systems have become a tool that cannot be ignored by websites with a large selection of products, music, news or simply webpages links. The performance of this kind of system depends on a large amount of information. At the same time, the amount of information on the Web is continuously growing, especially due to increased User Generated Content since the apparition of Web 2.0. In this paper, we propose a method that exploits blog textual data in order to supply a recommender system. The method we propose has two steps. First, subjective texts are labelled according to their expressed opinion in order to build a user-item-rating matrix. Second, this matrix is used to establish recommendations thanks to a collaborative filtering technique.