In this paper, we propose an approach for Stress Assignment in Spanish Proper Names, based on a Multi-Layer Perceptron (MLP). When assigning stress to a word, we first analyse each vowel in the word and then calculate a Stress-Confidence Measure for it, using a MLP. The system will assign the stress to the vowel with the highest stress-confidence measure. In this paper we present and analyse di...

Paradigmatic cases of proper name anomia and proper name selective sparing are reviewed from relevant neuropsychological literature. Available evidence supports the existence of functionally and anatomically distinct retrieval pathways for the categories of proper and common names. An information processing model whose main feature lies in the relative independence within the semantic-conceptua...

Identification and extraction of proper names from Internet-based sources currently suffers from a lack of verification methods that check the validity of these extracted names. A language-independent method for assigning probabilities to extracted proper names using frequency data harvested from the Internet is presented. Verification mechanisms are built on top of this technique to exclude mi...

Personal proper names are part of a community’s language inventory. To large extent, they verbalise gender stereotypes, expectations and norms, power relations, political circumstances, how minorities treated. In my paper I analyse the current socio-onomastic representation gender-neutral in context naming practices Czech Republic. More specifically, examine what factors might explain de...