What distributional semantics can (and cannot) tell us
                   about meaning

                                Alessandro Lenci 1
                       1 Università di Pisa and ILC-CNR, Italy




  Abstract. Distributional semantics is a mainstream research paradigm in com-
  putational linguistics and cognitive science. It is based on a simple assumption:
  Semantic representations of lexical items can be built by recording their distrib-
  ution in linguistic contexts. However, whether statistical co-occurrences alone
  are enough to address deep semantic questions, or whether they merely provide
  a shallow proxy of lexical meaning, remains an open question. In other words,
  what is the real descriptive and explanatory adequacy of distributional represen-
  tations of meaning? In this talk, I explore this issue by presenting some research
  themes that shed light on the potentialities and the current limits of distribution-
  al models of meaning. The first theme is the notion of semantic similarity. Dis-
  tributional semantics is based on the so-called Distributional Hypothesis stating
  that lexemes with similar linguistic contexts have similar meanings. However,
  distributional semantic models are actually more biased towards the much
  vaguer notion of semantic relatedness. The outcome of distributional models
  looks like a network of word associations, rather than a semantically structured
  space. This is an important weakness of current distributional semantic models.
  Though they have proven to be useful to capture various aspects of the mental
  lexicon, their limits in properly distinguishing different semantic relations also
  greatly impair the usability of distributional semantics to model logical infer-
  ences. A central aspect of human semantic competence is the ability to compose
  lexical meanings to form the interpretation of a potentially unlimited number of
  complex linguistic expressions. but compositionality is surely the “bottleneck”
  for distributional semantics. How distributional representations can be projected
  from the lexical to sentence or even discourse level is still an open issue. In this
  talk, I present a recent proposal of a distributional model of sentence compre-
  hension in which sentence meaning is built by dynamically activating and uni-
  fying distributional information about events and their participants.