The categorical compositional distributional model of Coecke et al. (2010) provides a linguistically motivated procedure for computing the meaning of a sentence as a function of the distributional meaning of the words therein. The theoretical framework allows for reasoning about compositional aspects of language and offers structural ways of studying the underlying relationships. While the mode...

An open problem with categorical compositional distributional semantics is the representation of words that are considered semantically vacuous from a distributional perspective, such as determiners, prepositions, relative pronouns or coordinators. This paper deals with the topic of coordination between identical syntactic types, which accounts for the majority of coordination cases in language...

Distributional learning research has established that humans can track the frequencies of sequentially presented stimuli in order to infer the probabilities of upcoming events (e.g., Hasher & Zacks, 1984). Here, we set out to explore anticipation of a stimulus after implicit distributional learning. We hypothesize that as people learn the category frequency information implicitly, response time...

Sometimes modifiers have a strong effect on core aspects of the meaning of the nouns they are attached to: A parrot is a desirable pet, but a dead parrot is, at the very least, a rather unusual household companion. In order to stimulate computational research into the impact of modification on phrase meaning, we collected and made available a large dataset containing subject ratings for a varie...

This chapter introduces context algebras and demonstrates their application to combining logical and vector-based representations of meaning. Other chapters in this volume consider approaches that attempt to reproduce aspects of logical semantics within new frameworks. The approach we present here is different: We show how logical semantics can be embedded within a vector space framework, and u...

Grammatical Abstract UngrammaticalUngrammatical Concrete Grammatical Concrete Ungrammatical Abstract Concrete 0.00 0.25 0.50 0.75 1.00Concrete 0.00 0.25 0.50 0.75 1.00 En do rs em en tr at es Grammatical

We introduce the problem of generation in distributional semantics: Given a distributional vector representing some meaning, how can we generate the phrase that best expresses that meaning? We motivate this novel challenge on theoretical and practical grounds and propose a simple data-driven approach to the estimation of generation functions. We test this in a monolingual scenario (paraphrase g...

I. abstract. In this note, we prove several multiplicative products of the n-dimensional Hankel transform. In fact the following formulae: H{δ (k) (u(x))}.H{δ () (u(x))} = DH δ (k++ n−2 2) (u(x)) , (III,1)