Autoencoding Pixies: Amortised Variational Inference with Graph Convolutions for Functional Distributional Semantics [PDF]
Functional Distributional Semantics provides a linguistically interpretable framework for distributional semantics, by representing the meaning of a word as a function (a binary classifier), instead of a vector.
Guy Edward Toh Emerson
semanticscholar +1 more source
Quantifier Scope in Categorical Compositional Distributional Semantics [PDF]
In previous work with J. Hedges, we formalised a generalised quantifiers theory of natural language in categorical compositional distributional semantics with the help of bialgebras.
Mehrnoosh Sadrzadeh
doaj +1 more source
Compositional Distributional Semantics with Syntactic Dependencies and Selectional Preferences
This article describes a compositional model based on syntactic dependencies which has been designed to build contextualized word vectors, by following linguistic principles related to the concept of selectional preferences.
Pablo Gamallo
doaj +1 more source
Functional Distributional Semantics [PDF]
Published at Representation Learning for NLP workshop at ACL 2016, https://sites.google.com/site/repl4nlp2016/
Emerson, G, Copestake, A
openaire +2 more sources
A Special Issue on Statistical and Logical Models of Meaning
In this special issue we collect five papers derived from the workshop on Statistical and Logical Models of Meaning (SaLMoM) celebrated 11th–15th July 2016 as part of the North American Summer School in Logic, Language and Information at Rutgers ...
Mehrnoosh Sadrzadeh, Glyn Morrill
doaj +1 more source
Using distributional semantics to study syntactic productivity in diachrony: A case study
Florent Perek
semanticscholar +3 more sources
Idiosyncratic frequency as a measure of derivation vs. inflection
There is ongoing discussion about how to conceptualize the nature of the distinction between inflection and derivation. A common approach relies on qualitative differences in the semantic relationship between inflectionally versus derivationally related
Maria Copot +2 more
doaj +1 more source
Event Knowledge in Compositional Distributional Semantics
The great majority of compositional models in distributional semantics present methods to compose vectors or tensors in a representation of the sentence.
Ludovica Pannitto, Alessandro Lenci
doaj +1 more source
Author's response: Mundari and argumentation in word-class analysis [PDF]
1. Introduction: Our three commentators raise such a host of deep and interesting issues that we cannot hope to answer them all within the time and space at our disposal.
Evans, Nicholas, Osada, Toshiki
core +1 more source
What do you mean, BERT? Assessing BERT as a Distributional Semantics Model [PDF]
Contextualized word embeddings, i.e. vector representations for words in context, are naturally seen as an extension of previous noncontextual distributional semantic models.
Timothee Mickus +3 more
semanticscholar +1 more source

