Automatic Extraction of Definitions in Portuguese: A Rule-Based Approach

Abstract

Abstract. In this paper we present a rule-based system for automatic extraction of definitions from Portuguese texts. As input, this system takes text that is previously annotated with morpho-syntactic information, namely on POS and inflection features. It handles three types of definitions, whose connector between definiendum and definiens is the so-called copula verb "to be", a verb other that one, or punctuation marks. The primary goal of this system is to act as a tool for supporting glossary construction in e-learning management systems. It was tested using a collection of texts that can be taken as learning objects, in three different domains: information society, computer science for non experts, and e-learning. For each one of these domains and for each type of definition typology, evaluation results are presented. On average, we obtain 14% for precision, 86% for recall and 0.33 for F 2 score.

Identifying Disease Definitions with a Correlation Kernel for Symptom Extractions from Text

“…The most popular is a series of work where rules are constructed based on syntactic patterns and templates are predefined to extract definitions. Examples are the effort to find definition sentences from Portuguese text based on morpho-syntactic information as well as words' inflections [10] and the research on using grammatical rules for identifying definition sentences ( [9], [23]). …”

Luščenje definicijskih kandidatov iz specializiranih korpusov

“…Drugi sklop raziskav se poslužuje metod strojnega učenja, pri čemer je odkrivanje definicij mogoče razumeti kot problem razvrščanja; algoritem se skuša iz učnega korpusa definicij, v nekaterih primerih pa tudi iz negativnih primerov nedefinicij, naučiti pravil za razlikovanje med pravimi in nepravimi definicijami. Z običajnimi klasifikacijskimi algoritmi, kot so naivni Bayes, odločitvena drevesa in metoda podpornih vektorjev, je različnim avtorjem uspelo razlikovati med dobro in slabo oblikovanimi definicijami (Del Gaudio, Branco 2007;Velardi in dr. 2008;Fahmi, Bouma 2006;Westerhout 2010;; Del Gaudio in dr. 2013 ter tudi naš poizkus v Fišer in dr. 2010), za popolnoma avtomatske pristope pa so bili uporabljeni tudi genetski algoritmi (Borg in dr. 2010) ter mreže besednih vrst (Navigli, Velardi 2010;Faralli, Navigli 2013).…”

"Medical Knowledge Organization System-Based Definition Generation and Visualization"

“…The age of big data speeds up the development of intelligent question and answering systems, especially in the biomedical field where a great deal of health data emerges all the time. While people search the basic meaning and intension of a medical terminology been adopted in several languages, for instance English [8], Chinese [9], German [10], Portuguese [11] and so on. And the particular implementation has been done either semi-automatically or fully automatically.…”