Aline Villavicencio

University of Sheffield y Universidade Federal do Rio Grande do Sul

Aline Villavicencio

University of Sheffield y Universidade Federal do Rio Grande do Sul

Nota biográfica

Aline Villavicencio es Catedrática en el Department of Computer Science de la University of Sheffield (UK), así como Profesora Adjunta en el Instituto de Informática de la Universidade Federal do Rio Grande do Sul (Brasil). Asimismo, es miembro de los equipos de investigación Neurocomputational and Natural Language Processing Laboratory (UFRGS) y Natural Language Processing Group (University of Sheffield). Sus principales áreas de investigación versan sobre semántica léxica, multilingualidad y PLN motivado cognitivamente. Su labor investigadora destaca por el uso de técnicas para el tratamiento de unidades plurilexemáticas mediante el empleo de métodos estadísticos y modelos de semántica distribucional, además de aplicaciones como Simplificación de Texto y Búsqueda de Respuestas, para lenguas tales como el inglés y el portugués.

 

Multiword Expressions Under the Microscope

Ranging from idioms (make ends meet), light verb constructions (take a shower) and verb particle constructions (shake up) to noun compounds (loan shark), Multiword Expressions (MWEs) have provided new challenges and opportunities for natural language processing. Their integration in tasks and applications like parsing, information retrieval, machine translation has brought improvements for language technology, providing a degree of precision, naturalness and fluency. In this talk I will present an overview of advances in the identification of MWEs, that often capitalize on the various degrees of idiosyncrasy they display, including lexical, syntactic, semantic and statistical. I will concentrate on techniques for identifying their degree of idiomaticity and approximating their meaning, as their interpretation often needs more knowledge than can be gathered from their individual components and their combinations to differentiate combinations whose meaning can be (partly) inferred from their parts (as apple juice: juice made of apples) from those that cannot (as dark horse: an unknown candidate who unexpectedly succeeds).