Estimating Linear Models for Compositional Distributional Semantics

By Fabio Massimo Zanzotto, Ioannis Korkontzelos, Francesca Fallucchi, Suresh Manandhar. 2010

156 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

Distributed Representations of Sentences and Documents (2014, methodology): “Representing phrases is a recent trend and received much attention (Mitchell & Lapata, 2010; Zanzotto et al., 2010; Yessenalina & Cardie, 2011; Grefenstette et al., 2013; Mikolov et al., 2013c).”
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank (2013, background): “Because they cannot capture the meaning of longer phrases properly, compositionality in semantic vector spaces has recently received a lot of attention (Mitchell and Lapata, 2010; Socher et al., 2010; Zanzotto et al., 2010; Yessenalina and Cardie, 2011; Socher et al., 2012; Grefenstette et al., 2013”
A Neural Network for Factoid Question Answering over Paragraphs (2014, background): “Many computational models of compositionality focus on learning vector spaces (Zanzotto et al., 2010; Erk, 2012; Grefenstette et al., 2013; Yessenalina and Cardie, 2011).”
From Paraphrase Database to Compositional Paraphrase Model and Back (2015, neutral): “Other works like Zanzotto et al. (2010) and Baroni and Zamparelli (2010) also explored composition using models based on operations of vectors and matrices.”
Recursive deep learning for natural language processing and computer vision (2014, background): “The RNNs of previous sections tackle the problem of compositionality in vector spaces which has been investigates by several researchers (Mitchell and Lapata, 2010; Baroni and Zamparelli, 2010; Zanzotto et al., 2010; Yessenalina and Cardie, 2011).”
Compositional-ly Derived Representations of Morphologically Complex Words in Distributional Semantics (2013, methodology): “This results in: − h i h i Guevara (2010) and Zanzotto et al. (2010) pro-pose the full additive model ( fulladd ), where the two vectors to be added are pre-multiplied by weight matrices: c = Au + Bv Since the Mitchell and Lapata and fulladd models were developed for phrase composition, the two…”
KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations (2020, background): “…human supervision (Cho et al., 2014; Kiros et al., 2015; Conneau et al., 2017; Subramanian et al., 2018; Cer et al., 2018) or are crafted with compositional distributional semantics methods (Clark and Pul-man, 2007; Mitchell and Lapata, 2008; Baroni and Zamparelli, 2010; Zanzotto et al., 2010).”
Global Belief Recursive Neural Networks (2014, background): “There has recently been a lot of work extending single word semantic vector spaces [27, 11, 16] to compositional models of bigrams [17, 29] or phrases of arbitrary length [25, 28, 24, 10].”
Distributional Models of Word Meaning (2018, background): “Other models carry out composition in DS by representing lexemes and phrases with matrices and tensors, rather than with vectors alone (Zanzotto et al. 2010, Socher et al. 2012).”
“Not not bad” is not “bad”: A distributional account of negation (2013, methodology): “Most efforts approach the problem of modelling phrase meaning through vector composition using linear algebraic vector operations (Mitchell and Lapata, 2008; Mitchell and Lapata, 2010; Zanzotto et al., 2010), matrix or tensor-based approaches (Baroni and Zamparelli, 2010; Coecke et al.”
Still a Pain in the Neck: Evaluating Text Representations on Lexical Composition (2019, background): “Zanzotto et al. (2010) and Dinu et al. (2013) extended this approach and composed any two words by multiplying each word vector by a composition matrix.”
Vector Space Models of Word Meaning and Phrase Meaning: A Survey (2012, methodology): “This method has become a standard baseline for other approaches to modeling two-word phrases, many of which focus specifically on modifier/noun pairs (Baroni and Zamparelli 2010; Guevara 2010, 2011; Zanzotto et al. 2010; Reddy et al. 2011; Hartung and Frank 2011; Washtell 2011).”
Vector Space Models of Lexical Meaning (2015, background): “Some additional work includes Widdows (2008); Zanzotto et al. (2010); Clarke (2012). The next section describes a framework, which, in contrast to the work mentioned above, provides a recipe for constructing phrase and sentence vectors in step with a syntactic, type-driven process.”
Semantic Compositionality through Recursive Matrix-Vector Spaces (2012, methodology): “…(Baroni and Lenci, 2010) 5. p = g ( W [ a ; b ]) , RNN, similar to Socher et al. 6. p = Ab + Ba , Linear MVR, similar to (Mitchell and Lapata, 2010; Zanzotto et al., 2010) 7. p = g ( W [ Ba ; Ab ]) , MV-RNN The ﬁnal distribution is always predicted by a softmax classiﬁer whose inputs p vary for…”
Have You Lost the Thread? Discovering Ongoing Conversations in Scattered Dialog Blocks (2017, background): “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).”
Category-theoretic quantitative compositional distributional models of natural language semantics (2013, background): “The first is the Generic Additive Model of [90].”