Open AccessProceedings Article
Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space
Marco Baroni,Roberto Zamparelli +1 more
- pp 1183-1193
TLDR
This work proposes an approach to adjective-noun composition (AN) for corpus-based distributional semantics that represents nouns as vectors and adjectives as data-induced (linear) functions over nominal vectors, and shows that the model significantly outperforms the rivals on the task of reconstructing AN vectors not seen in training.Abstract:
We propose an approach to adjective-noun composition (AN) for corpus-based distributional semantics that, building on insights from theoretical linguistics, represents nouns as vectors and adjectives as data-induced (linear) functions (encoded as matrices) over nominal vectors. Our model significantly outperforms the rivals on the task of reconstructing AN vectors not seen in training. A small post-hoc analysis further suggests that, when the model-generated AN vector is not similar to the corpus-observed AN vector, this is due to anomalies in the latter. We show moreover that our approach provides two novel ways to represent adjective meanings, alternative to its representation via corpus-based co-occurrence vectors, both outperforming the latter in an adjective clustering task.read more
Citations
More filters
Proceedings ArticleDOI
A Convolutional Neural Network for Modelling Sentences
TL;DR: A convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) is described that is adopted for the semantic modelling of sentences and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations.
Proceedings Article
Semantic Compositionality through Recursive Matrix-Vector Spaces
TL;DR: A recursive neural network model that learns compositional vector representations for phrases and sentences of arbitrary syntactic type and length and can learn the meaning of operators in propositional logic and natural language is introduced.
Proceedings ArticleDOI
Deep Unordered Composition Rivals Syntactic Methods for Text Classification
TL;DR: This work presents a simple deep neural network that competes with and, in some cases, outperforms such models on sentiment analysis and factoid question answering tasks while taking only a fraction of the training time.
Proceedings Article
A SICK cure for the evaluation of compositional distributional semantic models
Marco Marelli,Stefano Menini,Marco Baroni,Luisa Bentivogli,Raffaella Bernardi,Roberto Zamparelli +5 more
TL;DR: This work aims to help the research community working on compositional distributional semantic models (CDSMs) by providing SICK (Sentences Involving Compositional Knowldedge), a large size English benchmark tailored for them.
Posted Content
A Convolutional Neural Network for Modelling Sentences
TL;DR: This paper proposed the Dynamic Convolutional Neural Network (DCNN) which uses dynamic k-max pooling, a global pooling operation over linear sequences, to model sentences of varying length and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations.
References
More filters
Book
An introduction to the bootstrap
Bradley Efron,Robert Tibshirani +1 more
TL;DR: This article presents bootstrap methods for estimation, using simple arguments, with Minitab macros for implementing these methods, as well as some examples of how these methods could be used for estimation purposes.
Journal ArticleDOI
An Introduction to the Bootstrap.
Journal ArticleDOI
A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge.
TL;DR: A new general theory of acquired similarity and knowledge representation, latent semantic analysis (LSA), is presented and used to successfully simulate such learning and several other psycholinguistic phenomena.
Journal ArticleDOI
From frequency to meaning: vector space models of semantics
Peter D. Turney,Patrick Pantel +1 more
TL;DR: The goal in this survey is to show the breadth of applications of VSMs for semantics, to provide a new perspective on VSMs, and to provide pointers into the literature for those who are less familiar with the field.