Paper

Maila morfosintaktikoan etiketatutako euskarazko corpusen desanbiguatze-lanetan urtetan aritu ondoren, bide horretan topatutako hainbat zailtasunen berri emango dugu artikulu honetan eta, horrekin batera, hainbat irizpide birplanteatzeko beharra ere azalduko dugu. Testuingurua hizkuntzalaritza konputazionala izanik, guk erabilitako metodologia erregeletan oinarritutako gramatikena da, hau da, informazio linguistikoa baliatuz aurrera eramaten dena.

This work describes the formalization of a word structure grammar that represents the complex morphological and morphosyntactic information embedded within the word forms of an agglutinative language (Basque), giving a comprehensive linguistic description of the main morphological phenomena, such as affixation, derivation, and composition, and also taking into account the modeling of both standard and non standard words. We have identified the relevant issues to be addressed in the representation of such a grammar.

Zero-shot learning is a very promising research topic. For a vision-based action recognition system, for instance, zero-shot learning allows to recognise actions never seen during the training phase. Previous works in zero-shot action recognition have exploited in several ways the visual appearance of input videos to infer actions. Here, we propose to add external knowledge to improve the performance of purely vision-based systems. Specifically, we have explored three different sources of knowledge in the form of text corpora.

In this article, we explain the first steps to-wards a grammar-helping tool for Basquefrom a ruled-based approach. Specifically,we show the first steps carried out for help-ing with verb agreement, some of the dif-ficulties encountered, which linguistic is-sues arise when new rules are designed,and future perspectives