Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space

By Marco Baroni, Roberto Zamparelli. 2010

570 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

A Convolutional Neural Network for Modelling Sentences (2014, background): “…cases, a composition function is learned and either tied to particular syntactic relations (Guevara, 2010; Zanzotto et al., 2010) or to particular word types (Baroni and Zamparelli, 2010; Coecke et al., 2010; Grefenstette and Sadrzadeh, 2011; Kart-saklis and Sadrzadeh, 2013; Grefenstette, 2013).”
A SICK cure for the evaluation of compositional distributional semantic models (2014, background): “…DSMs, or CDSMs) have been proposed, with the purpose of representing the meaning of phrases and sentences by composing the distributional representations of the words they contain (Mitchell and Lapata, 2010; Baroni and Zamparelli, 2010; Grefenstette and Sadrzadeh, 2011; Socher et al., 2012).”
SemEval-2014 Task 1: Evaluation of Compositional Distributional Semantic Models on Full Sentences through Semantic Relatedness and Textual Entailment (2014, background): “Recently, several compositional extensions of DSMs (CDSMs) have been proposed, with the purpose of representing the meaning of phrases and sentences by composing the distributional representations of the words they contain (Baroni and Zamparelli, 2010; Grefenstette and Sadrzadeh, 2011; Mitchell and ”
Illinois-LH: A Denotational and Distributional Approach to Semantics (2014, background): “Following recent work that extends distributional similarities to phrases and sentences (Mitchell and Lapata, 2010; Baroni and Zamparelli, 2010; Grefenstette and Sadrzadeh, 2011; Socher et al., 2012), we deﬁne a phrase vector p to be the pointwise multiplication product of the vectors of the words…”
Multilingual Distributed Representations without Word Alignment (2013, background): “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]).”
Recurrent Convolutional Neural Networks for Discourse Compositionality (2013, methodology): “With regard to modelling the meaning of sentences and sentential compositionality, recent proposals have included simple additive and multiplicative models that do not take into account sentential features such as word order or syntactic structure (Mitchell and Lapata, 2010), matrix-vector based mod”
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 ).”
Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model (2015, methodology): “We refer here not only to the results reported in Baroni et al. (2014b), but also to the more extensive evaluation that Baroni and colleagues present in the companion website (http://clic.”
Multi-Step Regression Learning for Compositional Distributional Semantics (2013, methodology): “Multi-step regression learning is a generalisation of linear regression learning for tensors of rank 3 or higher, as procedures already exist for tensors of rank 1 (lexical semantic vectors) and rank 2 (Baroni and Zamparelli, 2010).”
From Paraphrase Database to Compositional Paraphrase Model and Back (2015, methodology): “Other works like Zanzotto et al. (2010) and Baroni and Zamparelli (2010) also explored composition using models based on operations of vectors and matrices.”
Normalized Word Embedding and Orthogonal Transform for Bilingual Word Translation (2015, background): “Following the idea that the meaning of a word can be determined by ‘the company it keeps’ (Baroni and Zamparelli, 2010), i.”
Domain and Function: A Dual-Space Model of Semantic Relations and Compositions (2012, background): “Baroni and Zamparelli (2010) and Guevara (2010) suggest another model of composition for adjective-noun phrases.”
Have You Lost the Thread? Discovering Ongoing Conversations in Scattered Dialog Blocks (2017, methodology): “Many models have been proposed (Mitchell and Lapata 2008; Baroni and Zamparelli 2010; Clark et al. 2008; Grefenstette and Sadrzadeh 2011; Zanzotto et al. 2010; Socher et al. 2011, 2012; Kalchbrenner and Blunsom 2013).”
A case for deep learning in semantics: Response to Pater (2019, background): “…al. 2012, Socher et al. 2013), building on early work on recursive connectionist architectures (Pollack 1990, Smolensky 1990, Plate 1994, Goller & Küchler 1996) and on compositional distributional semantics (Baroni & Zamparelli 2010, Mitchell & Lapata 2010; for an overview, see Baroni et al. 2014).”
Fracking Sarcasm using Neural Network (2016, background): “(Guevara, 2010) and (Malakasiotis, 2011) formulated their composition function using a set of specific syntactic relations or specific word categories (Baroni and Zamparelli, 2010).”
Compositional Operators in Distributional Semantics (2014, methodology): “In the context of their work with adjectives (shortly discussed in Section 6), Baroni and Zamparelli (2010) performed an interesting experiment along these lines using the ukWaC corpus, consisted of 2.8 billion words. As we saw, their work follows the tensor-based paradigm where adjectives are repre”