DeepAI AI Chat
Log In Sign Up

Composing and Embedding the Words-as-Classifiers Model of Grounded Semantics

by   Daniele Moro, et al.

The words-as-classifiers model of grounded lexical semantics learns a semantic fitness score between physical entities and the words that are used to denote those entities. In this paper, we explore how such a model can incrementally perform composition and how the model can be unified with a distributional representation. For the latter, we leverage the classifier coefficients as an embedding. For composition, we leverage the underlying mechanics of three different classifier types (i.e., logistic regression, decision trees, and multi-layer perceptrons) to arrive at a several systematic approaches to composition unique to each classifier including both denotational and connotational methods of composition. We compare these approaches to each other and to prior work in a visual reference resolution task using the refCOCO dataset. Our results demonstrate the need to expand upon existing composition strategies and bring together grounded and distributional representations.


page 3

page 7


Aligning Packed Dependency Trees: a theory of composition for distributional semantics

We present a new framework for compositional distributional semantics in...

Resolving References to Objects in Photographs using the Words-As-Classifiers Model

A common use of language is to refer to visually present objects. Modell...

No Word is an Island -- A Transformation Weighting Model for Semantic Composition

Composition models of distributional semantics are used to construct phr...

Learning Functional Distributional Semantics with Visual Data

Functional Distributional Semantics is a recently proposed framework for...

A Systematic Comparison of English Noun Compound Representations

Building meaningful representations of noun compounds is not trivial sin...

A Unified Semantic Embedding: Relating Taxonomies and Attributes

We propose a method that learns a discriminative yet semantic space for ...

Improving Semantic Composition with Offset Inference

Count-based distributional semantic models suffer from sparsity due to u...