This paper presents few extensions to the logic form representation and a method for transforming WordNet glosses into logic forms using a set of high-precision rules combined with a set of high recall heuristics. An almost 3% increase in POS tagging accuracy is achieved over state-of-the art results at the expense of user intervention on only 7.52% of words. We apply a nearest neighbor solutio...

2 Abbreviations used in the glosses: dem = demonstrative pronoun, n = neuter, nn = nonneuter, sg = singular, pl = plural, inv = inversion form, pcple = past participle.

We propose and evaluate a new paradigm for machine translation of low resource languages via the learned surface transduction and paraphrase of multilingual glosses.

Adjectives are one of the major contributors to conveying subjective meaning to sentences. Understanding the semantics of adjectives is essential for understanding natural language sentences. In this paper we propose a novel approach for learning different properties that an adjective can describe, corresponding to the ‘attribute concepts’, which is not currently available in existing linguisti...

In this paper we present the Spanish version of WordNet 3.0. The English resource includes the glosses (definitions and examples) and the labelling of senses with WordNet identifiers. We have translated the synsets and the glosses to Spanish and alignment has been carried out at word level, whenever possible. The project has produced two interesting results: we have obtained a bilingual (Spanis...