Acronym identification in Greek legal texts

The use of acronyms is common in several document categories. With acronyms we avoid the repetitive use of long cumbersome titles and simplify some very wordy and verbose texts. In formal types of texts (e.g. in academic writing), two approaches are used to properly define acronyms within a text. For longer stand-alone works, like a textbook or a thesis, a list of definitions and acronyms used throughout the text is sometimes included near the beginning of the work (e.g. after the table of contents). In shorter texts [e.g. request for comments (RFC), medical, legislation texts], a more direct method of defining acronyms is adopted: acronyms are usually defined at the first point of use in the text with a parenthetical reference after the full title. Unfortunately, not all writers comply with the aforementioned approaches. It is very common for a writer to use unidentified acronyms presupposing that all readers share a common knowledge field (usually the thematic domain of the text) that contains the acronyms’ meanings. But often, this is partially true (or totally false) and the interpretation of some acronyms becomes ambiguous or impossible. In such cases, disambiguation methods can be implemented to support readers (Pustejovsky et al. , 2001; Joshi et al. , 2006; Sumita and Sugaya, 2006). In particular, search engines can help at the identification process regarding acronym definitions, for example, http://www.asas.gr/ (accessed February 2013). However, for all these tools to function properly, they need a knowledge base of acronyms along with their definitions, which is not always available, at least not in every specific topic and not in every language. In this article, we are concerned with legal texts in Modern Greek. According to the Hellenic Organization for Standardization S.A. (http://www.elot.gr, accessed February 2013), there is no standardization on how to create …