Research Meeting: Pia Sommerauer
Polysemy (and metaphorical mappings) in computational models of meaning representation
In this talk, computational approaches will be introduced to representing word meaning and, in particular, polysemy, which is one of the core aspects of Pia’s PhD project. Polysemy is a semantic phenomenon that affects a vast number of problems in Natural Language Processing (NLP), including the automatic identification and interpretation of metaphors. In this (probably interactive) talk, Pia aims at introducing how different computational approaches to representing word meaning deal with polysemy. In particular, the way distributional models (i.e. models that are purely based on words as they appear in linguistic corpora) represent words and how they are affected by polysemy (and, possibly, metaphorical mappings between domains) will be presented. If there is time, a demo of automatic word sense disambiguation based on a distributional model of word meaning with some examples will be shown. Perhaps we can have a discussion about the strengths and weaknesses of the approaches.