This report describes a series of exploratory experiments to establish whether terms of
different semantic type can be distinguished in useful ways in a semantic space constructed …

Languages are not uniform. Speakers of different language varieties use certain words
differently–more or less frequently, or with different meanings. We argue that distributional …

Some words are more contentful than others: for instance, make is intuitively more general
than produce and fifteen is more 'precise'than a group. In this paper, we propose to measure …

In this paper we present a novel application of compositional distributional semantic models
(CDSMs): prediction of lexical typology. The paper introduces the notion of typological …

A large amount of literature on conceptual abstraction has investigated the differences in
contextual distribution (namely “contextual variability”) between abstract and concrete …

Measuring the semantic similarity and relatedness of words can play a vital role in many
natural language processing tasks. Distributional semantic models computing these …

This thesis is concerned with the measurement and application of lexical distributional
similarity. Two words are said to be distributionally similar if they appear in similar contexts …

This paper queries which aspects of lexical semantics can reasonably be expected to be
modelled by corpus-based theories such as distributional semantics or techniques such as …

What do powerful models of word mean-ing created from distributional data (eg Word2vec
(Mikolov et al., 2013) BERT (Devlin et al., 2019) and ELMO (Peters et al., 2018)) represent …

Distributional semantics embodies the idea that the context in which a word occurs reveals
the meaning of that word. In contemporary corpus linguistics, that idea takes shape in …