Combining Symbolic and Distributional Models of Meaning

By Stephen Clark, Stephen G. Pulman. 2007

152 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.”
Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning (2018, background): “Clark & Pulman (2007) combine symbolic and distributed representations of words using tensor products.”
From Frequency to Meaning: Vector Space Models of Semantics (2010, methodology): “Clark and Pulman (2007) assigned distributional meaning to sentences using the Hilbert space tensor product.”
Injecting Logical Background Knowledge into Embeddings for Relation Extraction (2015, background): “Several studies have investigated the use of symbolic representations (such as dependency trees) to guide the composition of distributed representations (Clark and Pulman, 2007; Mitchell and Lapata, 2008; Coecke et al., 2010; Hermann and Blunsom, 2013).”
Experimental Support for a Categorical Compositional Distributional Model of Meaning (2011, background): “…multiplication ( (cid:12) , cf. § 4 for details) are commutative, hence if Non-commutative operations, such as the Kronecker product ( cf. § 4 for deﬁnition) can take word-order into account (Smolensky, 1990) or even some more complex syntactic relations, as described in Clark and Pulman (2007).”
Multilingual Distributed Representations without Word Alignment (2013, methodology): “Subsequent work has also attempted to learn distributed semantics of larger structures, allowing us to apply distributed representation to tasks such as sentiment analysis or paraphrase detection (i.a. [1, 3, 12, 14, 21, 25]).”
Distributional Memory: A General Framework for Corpus-Based Semantics (2010, positive): “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).”
Multilingual Models for Compositional Distributed Semantics (2014, background): “A CVM learns semantic representations of larger syntactic units given the semantic representations of their constituents (Clark and Pulman, 2007; Mitchell and Lapata, 2008; Baroni and Zamparelli, 2010; Grefenstette and Sadrzadeh, 2011; Socher et al., 2012; Hermann and Blunsom, 2013, inter alia ).”
Domain and Function: A Dual-Space Model of Semantic Relations and Compositions (2012, neutral): “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.”
Mathematical Foundations for a Compositional Distributional Model of Meaning (2010, methodology): “connectionist and symbolic models of mind, [6] argued for the use of the tensor product of vector spaces and pairing the vectors of meaning with their roles.”
Distributional techniques for philosophical enquiry (2012, methodology): “that building on the relatively recent and novel research in composing distributions (Clark and Pulman, 2007), we can computationally illustrate the main thesis advocated by researchers on intersectionality.”
Compositional Operators in Distributional Semantics (2014, background): “As Pulman (2013) mentions: “It is worth pointing out that a corpus of 2.83 billion is already thousands of times as big as the number of words it is estimated a 10-year-old person would have been exposed to (Moore, 2003), and many hundreds of times larger than any person will hear or read in a lifet”
A Context-Theoretic Framework for Compositionality in Distributional Semantics (2011, background): “Approaches to the task of recognizing textual entailment, including the use of subsequence matching, lexical entailment probability, and latent Dirichlet allocation, can be described within our framework.”
Compositional Matrix-Space Models of Language (2010, background): “Clark and Pulman (2007) suggest a conceptual model which unites symbolic and distributional representations by means of traversing the parse tree of a sentence and applying a tensor product for combining vectors of the meanings of words with the vectors of their roles.”
Composition in Distributional Models of Semantics (2010, background): “Tensor products have been recently proposed as an alternative to vector addition (Aerts & Czachor, 2004; Clark & Pulman, 2007; Widdows, 2008).”