"Machine Learning and Natural Language Processing"
Vito Pirreli
ILP-CNR, Area della Ricerca CNR, Pisa, Italy
Biography
European Chair of "NetWordS: the European Network on Word Structure", European Science Foundation Research Networking Programme, Member of the Editorial Board of “Lingue e Linguaggio”, Member of the Editorial Board of "Linguistica Computazionale", Member of the Scientific Board of the Centre for Post-doc Research and Education “The languages of Europe: Typology, History and Sociolinguistics” (LETISS), Member of the Scientific Committee of ILC, Head of the CNR Dylan Lab, Head of the CNR strategic project “Bio-computational models of language and cognition”.
Abstract:
Machine learning and neurolinguistic issues in language processing
Over the last decades, a growing body of evidence on the mechanisms governing lexical storage, access, acquisition and processing has questioned traditional models of language architecture and word usage based on the hypothesis of a direct correspondence between modular components of grammar competence (lexicon vs. rules), processing correlates (memory vs. computation) and neuro-anatomical localisations (prefrontal vs. temporo-parietal perisylvian areas of the left hemisphere). A new view appears to support a considerably more distributed and integrative picture, whereby words in the mental lexicon are emergent properties of the functional interaction between different brain regions. In the talk I will explore the implications of these recent acquisitions for issues of machine language learning and language architecture.