In this paper we present a progress report of the OntoWordNet project, a research program aimed at achieving a formal specification of WordNet. Within this program, we developed a hybrid bottom-up top-down methodology to automatically extract association relations from WordNet, and to interpret those associations in terms of a set of conceptual relations, formally defined in the DOLCE foundatio...

This document describes the Word Sense Disambiguation system used by Language Computer Corporation at English Coarse Grained All Word Task at SemEval 2007. The system is based on two supervised machine learning algorithms: Maximum Entropy and Support Vector Machines. These algorithms were trained on a corpus created from SemCor, Senseval 2 and 3 all words and lexical sample corpora and Open Min...

This paper describes a case study on methods for automatically extracting qualia relations from dictionary glosses in Italian, namely the Senso Comune De Mauro Dictionary (SCDM). The qualia extraction has been addressed by means of a pattern-based approach and lexical match with an Italian generative lexicon based language resource, PAROLE-SIMPLECLIPS (PSC). The evaluation of the extraction app...

Revisiting my research project from 19 years ago, which deals with notions of integrity in architectural creative processes, this article reflects upon the underlying techniques forms spatial writing, as part ongoing doctoral thesis work. I approach writing now a process ordering references and thoughts for inspection, relation to textile-like patterns that created previous concluded licentiate...

Designing appropriate materials and activities to enhance vocabulary learning is one of the primary goals of language courses. Among the claims about efficient pedagogical tasks is the Involvement Load Hypothesis (Laufer & Hulstijn, 2001) according to which vocabulary development is contingent on the amount of cognitive process a task involves. Building on the previous research on this hypothes...

This paper describes one of the approaches how to overcome some major limitations of current fulltext search engines. It tries to discover semantic categories for proper nouns from WordNet glosses and verify them with Yahoo and Google. It relies on lexical patterns present in large repositories and it is inspired by Pankow [2]. It follows the paper from student workshop in April 2006 [6]. Some ...

Linking concepts and named entities to knowledge bases has become a crucial Natural Language Understanding task. In this respect, recent works have shown the key advantage of exploiting textual definitions in various Natural Language Processing applications. However, to date there are no reliable large-scale corpora of sense-annotated textual definitions available to the research community. In ...

We propose a method that uses information from WordNet glosses to assign semantic tags to individual word meanings, rather than to entire words. The produced lists of annotated words will be used in sentiment annotation of texts and phrases and in other NLP tasks. The method was implemented in the Semantic Tag Extraction Program (STEP) and evaluated on the category of sentiment (positive, negat...