Towards the Automatic Identification of Spanish Verbal Phraseological Units Bel´ em Priego S´ anchez 1,2 , David Pinto 2 and Salah Mejri 1 1 LDI, Universit´ e Paris 13, Sorbonne Paris Cit´ e Paris, France belemps@gmail.com, smejri@ldi.univ-paris13.fr 2 Benem´ erita Universidad Aut´onoma de Puebla, FCC Puebla, Pue., M´ exico dpinto@cs.buap.mx Abstract. Verbal Phraseological Units are expressions made up of two or more words in which at least one of these words is a verb that plays the role of the predicate. Their main attribute is that this form of expression has taken on a more specific meaning than the expression itself. The automatic recognition of this type of linguistic structures is a very important task, since they are the standard way of expressing a concept or idea. This paper describes the outgoing advances of a PhD research work in which it is attempted to construe a methodology which allows to automatically identify these linguistic structures for the Mexican Spanish language. It is presented a set of hypotheses which will allow to produce novel proposals in the way of automatically identifying a verbal phraseological unit in a raw text. Additionally, we have presented experiments carried out in this sense, for example, by employing machine learning methods. Finally, we show a lexical resource which is product of the current advances in this PhD thesis. Keywords: Verbal phraseological units, Automatic identification, Cor- pus linguistics. 1 Introduction Some concepts are expressed in language through set of words or phrases, which intuitively are employed native speakers, thus characterizing different cultural communities. Phraseology, considered a cultural heritage of the linguistic com- munity [8], aims to study these blocks of words, which are usually refered as phraseological units. The study of phraseological units has a growing importance in recent years, in part because the linguistic and computational linguistic community has under- stood that this phenomenon covers all the sentence components [11], a fact that involves different dimensions of the natural language: linguistics, pragmatics, culturals, among others [12]. A phraseological unit is basically one type of multiword expression, and under this denomination one assumes a wide range 65 Research in Computing Science 96 (2015) pp. 65–73; rec. February 27, 2015; acc. May 22, 2015