Building a shared world: mapping distributional to model-theoretic semantic spaces

By Aurélie Herbelot, Eva Maria Vecchi. 2015

73 citations recorded by the source corpus.

In this paper, we introduce an approach to automatically map a standard distributional semantic space onto a set-theoretic model. We predict that there is a functional relationship between distributional information and vectorial concept representations in which dimensions are predicates and weights are generalised quantifiers. In order to test our prediction, we learn a model of such relationship over a publicly available dataset of feature norms annotated with natural language quantifiers. Our initial experimental results show that, at least for domain-specific data, we can indeed map between formalisms, and generate high-quality vector representations which encapsulate set overlap information. We further investigate the generation of natural language quantifiers from such vectors.

Subfields: Artificial Intelligence, Molecular Biology, Computational Linguistics & Semantics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

In Computational Linguistics & Semantics

Citations in the corpus

Rationalizing Neural Predictions (2016, background): “…analyzing and visualizing state activation (Hermans and Schrauwen, 2013; Karpathy et al., 2015; Li et al., 2016), learning sparse interpretable word vectors (Faruqui et al., 2015b), and linking word vectors to semantic lexicons or word properties (Faruqui et al., 2015a; Herbelot and Vecchi, 2015).”
Understanding Neural Networks through Representation Erasure (2016, background): “, 2012), linking dimensions with semantic lexicons or word properties (Faruqui et al., 2014; Herbelot and Vecchi, 2015), learning sparse interpretable word vectors (Faruqui et al.”
Are Distributional Representations Ready for the Real World? Evaluating Word Vectors for Grounded Perceptual Meaning (2017, neutral): “Several studies have used distributional representations to reconstruct aspects of these semantic norm datasets (Herbelot and Vecchi, 2015; Fagarasan et al., 2015; Erk, 2016).”
Ten Pairs to Tag – Multilingual POS Tagging via Coarse Mapping between Embeddings (2016, background): “One advantage is that this preserves cosine similarity between vectors, which is viewed as a proxy for syntactic/semantic similarity (Mikolov et al., 2013a; Pennington et al., 2014; Herbelot and Vecchi, 2015).”
“Look, some Green Circles!”: Learning to Quantify from Images (2016, background): “Quantiﬁers are an emerging ﬁeld of research in distributional semantics (Grefenstette, 2013; Herbelot and Vecchi, 2015) and, so far, haven’t been studied in relation with visual data and grounding.”
Rotated Word Vector Representations and their Interpretability (2017, background): “Since distributed representations play an important role in various NLP tasks, they are applied to semantics (Herbelot and Vecchi, 2015; Qiu et al., 2015; Woodsend and Lapata, 2015), with incorporating external information to them (Tian et al.”
Formal Distributional Semantics: Introduction to the Special Issue (2016, background): “…logic (Grefenstette 2013); (b) a mapping function from a distributional semantics space to some heavily underspeciﬁed form of a “model-theoretic” space (Herbelot and Vecchi 2015); (c) a function from sentences in a discourse to other sentences in the same discourse (Capetola 2013) (i.e., for…”