Semantic Vector Products: Some Initial Investigations

By Dominic Widdows. 2008

117 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank (2013, background): “Some related models such as holographic reduced representations (Plate, 1995), quantum logic (Widdows, 2008), discrete-continuous models (Clark and Pulman, 2007) and the recent compositional matrix space model (Rudolph and Giesbrecht, 2010) have not been experimentally validated on larger corpora.”
Distributional Memory: A General Framework for Corpus-Based Semantics (2010, neutral): “A general consensus exists on the need to overcome this limitation, and to build new bridges between corpus-based semantics and symbolic models of meanings (Clark and Pulman 2007; Widdows 2008).”
Domain and Function: A Dual-Space Model of Semantic Relations and Compositions (2012, methodology): “Another approach is to use a tensor product for composition (Smolensky, 1990; Aerts & Czachor, 2004; Clark & Pulman, 2007; Widdows, 2008), such as the outer product, C = a⊗ b.”
Composition in Distributional Models of Semantics (2010, methodology): “Tensor products have been recently proposed as an alternative to vector addition (Aerts & Czachor, 2004; Clark & Pulman, 2007; Widdows, 2008).”
Context-theoretic Semantics for Natural Language: an Overview (2009, methodology): “Various ways of composing vector based representations of meaning were investigated by Widdows (2008), including the tensor product and direct sum.”
Semantic Compositionality through Recursive Matrix-Vector Spaces (2012, background): “Other important models are tensor products (Clark and Pulman, 2007), quantum logic (Widdows, 2008), holographic reduced representations (Plate, 1995) and the Compositional Matrix Space model (Rudolph and Giesbrecht, 2010).”
Recursive deep learning for natural language processing and computer vision (2014, background): “Some related models such as holographic reduced representations (Plate, 1995), quantum logic (Widdows, 2008), discrete-continuous models (Clark and Pulman, 2007) and the recent compositional matrix space model (Rudolph and Giesbrecht, 2010) have not been experimentally validated on larger corpora.”
Vector Space Models of Lexical Meaning (2015, background): “Some additional work includes Widdows (2008); Zanzotto et al. (2010); Clarke (2012) .”
Category-theoretic quantitative compositional distributional models of natural language semantics (2013, background): “However, it is important to note that [87] considers possible linguistic application areas where they may be of use, although once again these mostly involve noun-verb and adjective-noun compositionality rather than full-blown sentence vector construction.”
Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space (2010, unknown): “…2007; Sahlgren et al., 2008) or sophisticated composition methods based on tensor products, quantum logic, etc., that have not yet been empirically tested on large-scale corpus-based semantic space tasks (Clark and Pulman, 2007; Rudolph and Giesbrecht, 2010; Smolensky, 1990; Widdows, 2008).”
Compositional Matrix-Space Models of Language (2010, methodology): “Widdows (2008) proposes a number of more advanced vector operations well-known from quantum mechanics, such as tensor product and convolution, to model composition in vector spaces.”