Frege in Space: A Program of Compositional Distributional Semantics

By Marco Baroni, Raffaella Bernardi, Roberto Zamparelli. 2014

222 citations recorded by the source corpus.

Subfields: Natural Language Processing, Computational Linguistics & Semantics

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 Computational Linguistics & Semantics

Citations in the corpus

Towards Universal Paraphrastic Sentence Embeddings (2015, background): “Some have been based on distributional semantics (Baroni et al., 2014; Paperno et al., 2014; Polajnar et al., 2015; Tian et al., 2015), while the current trend is toward development of neural network architectures.”
Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model (2015, methodology): “The recent evaluation of Baroni et al. (2014b) suggests that the C-BOW model introduced by Mikolov et al. (2013a) is, consistently, the best across many tasks.”
Distributional Models of Word Meaning (2018, methodology): “In particular, the lexical function model aims to establish a direct link with Montague grammar by proposing a linear-algebraic representation of type-theoretic objects (Coecke et al. 2011, Baroni et al. 2014a, Grefenstette & Sadrzadeh 2015, Rimell et al. 2016).”
Word meaning in minds and machines (2020, background): “Linear transformations can account for more subtle transformations, including adjectives that emphasize one property for some types of nouns and another property for other types of nouns (Baroni et al., 2014).”
Building a shared world: mapping distributional to model-theoretic semantic spaces (2015, background): “…from these considerations, suggesting that an overarching semantics integrating both distributional and formal aspects would be desirable (Coecke et al., 2011; Bernardi et al., 2013; Grefenstette, 2013; Baroni et al., 2014a; Garrette et al., 2013; Beltagy et al., 2013; Lewis and Steedman, 2013).”
Formal Distributional Semantics: Introduction to the Special Issue (2016, background): “Some aspects of logical operators, in fact, can even be directly derived from their vectors: Baroni et al. (2012) show that, to a reasonable extent, entailment relations between a range of quantifiers can be learned from their distributions.”
Can recursive neural tensor networks learn logical reasoning? (2013, background): “Much of the work to date analyzing vector representations for words (see [5]) has focused on lexical semantic behaviors—like the similarity between words like Paris and France .”
An Exploration of Discourse-Based Sentence Spaces for Compositional Distributional Semantics (2015, methodology): “In contrast, there has been little investigation of different distributional representations for sentences, though the current hypothesis is that the wider discourse in which the sentence is situated may provide relevant information (Baroni et al., 2014; Clark, 2013, 2015).”
How to marry a star: Probabilistic constraints for meaning in context (2020, methodology): “…(Asher 2011), attribute-value matrices (Zeevat et al. 2017), qualia (Del Pinal 2018) and, frequently, distributional models automatically computed from corpus data (Grefenstette & Sadrzadeh 2011, Baroni et al. 2014, Erk 2016, Asher et al. 2016, McNally & Boleda 2017, Emerson 2020a, Herbelot 2020).”