"Distributional Models of German Noun Compounds and Particle Verbs"

Distributional models assume that the contexts of a linguistic unit
(such as a word, a multi-word expression, a phrase, a sentence, etc.)
provide information about the meaning of the linguistic unit (Harris,
1954; Firth, 1957). They have been widely applied in data-intensive
lexical semantics (among other areas), and proven successful in
diverse research issues, such as the representation and disambiguation
of word senses; selectional preference modelling; the compositionality
of compounds and phrases, or as a general framework across semantic
tasks.

In this talk, I will present ongoing work that explores the potential
and the limits of distributional models for German multi-word
expressions (MWEs), focusing on noun-noun compounds and particle
verbs. We are interested in the compositionality of the MWEs; more
specifically, we aim to predict the degree of compositionality of the
MWEs and to determine the contributions of the constituents to the MWE
meanings. In this vein, I will describe both experiential data and
distributional models, including collections of compositionality
ratings, cognitive experiments to explore the meanings of the
constituents, and computational co-occurrence and clustering models to
discriminate potentially ambiguous MWE and constituent meanings and
meaning shifts.