Alessandro Lenci

TL;DR: This work presents the general architecture and features of MILE, as well as the methodology adopted for its definition, and focuses on two essential ingredients for the MILE specification: the selection of the types of lexical information most relevant to establish multili ngual correspondences, and the specification of a data structure which will provide the formal backbone of theMILE as a general representation language to develop multili Ngual resources.

TL;DR: Universal Dependencies as discussed by the authors is a project that aims to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, crosslingual learning, and parsing research from a language typology perspective.

TL;DR: The aim of this paper is to introduce LexIt, a computational framework for the automatic acquisition and exploration of distributional information about Italian verbs, nouns and adjectives, freely available through a web interface at the address http://sesia.humnet.unipi.it/lexit.

TL;DR: Distributional semantic models are used to explore the complex interplay between linguistic and affective information in the representation of abstract words and show that abstract words have more affective content and tend to co-occur with contexts with higher emotive values.

TL;DR: A series of new results on corpus derived semantic representations based on vectors of simple word co-occurrence statistics, with particular reference to word categorization performance as a function of window type and size, semantic vector dimension, and corpus size are presented.