Entailment above the word level in distributional semantics

By Marco Baroni, Raffaella Bernardi, Ngoc-Quynh Do, Chung-chieh Shan. 2012

258 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.

Citations in the corpus

Word Representations via Gaussian Embedding (2014, methodology): “We include the best F1 score (by picking the optimal threshold at test) because this is used by Baroni et al. (2012), but we believe AP is better to demonstrate the correlation of various asymmetric and symmetric measures with the entailment data.”
Recursive Neural Networks Can Learn Logical Semantics (2014, background): “Past experimental work on reasoning with distributed representations have been largely confined to short phrases (Mitchell and Lapata, 2010; Grefenstette et al., 2011; Baroni et al., 2012).”
Recursive Neural Networks for Learning Logical Semantics (2014, background): “To date, experimental investigations of these concepts using distributed representations have been largely conﬁned to short phrases [9, 10, 11, 12].”
Separated by an Un-common Language: Towards Judgment Language Informed Vector Space Modeling (2015, methodology): “We applied the same sive list of these datasets, as well as of evaluation sets for word relations beyond word pair similarity and association (Mitchell and Lapata, 2008; Bruni et al., 2012; Baroni et al., 2012, inter alia), is given at http://wordvectors.org/suite.php.”
Context Mover's Distance & Barycenters: Optimal transport of contexts for building representations (2018, unknown): “…on 10 standard datasets: BLESS (Baroni & Lenci, 2011), EVALution (Santus et al., 2015), (Benotto, 2015), (Weeds et al., 2014), BIBLESS (Kiela et al., 2015), (Baroni et al., 2012), (Kotlerman et al., 2010), (Levy et al., 2014), HypeNet-Test (Shwartz et al., 2016), and (Turney & Mohammad, 2015).”
Most “babies” are “little” and most “problems” are “huge”: Compositional Entailment in Adjective-Nouns (2016, methodology): “This assumption has been exploited by high-performing RTE systems (MacCartney and Manning, 2008; Stern and Dagan, 2012), as well as used as the basis for learning new entailment rules (Baroni et al., 2012; Young et al., 2014).”
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.”
Bringing Machine Learning and Compositional Semantics Together (2015, background): “…many important, relevant developments in semantic representation (de Marneffe et al. 2006; MacCartney & Manning 2009; van Eijck & Unger 2010; Palmer et al. 2010), semantic interpretation (Dagan et al. 2006; Sauŕı & Pustejovsky 2009), and structured prediction (Baklr et al. 2010; Smith 2011).”
Order-Embeddings of Images and Language (2015, background): “The most similar evaluation has been that of Baroni et al. (2012), who use external linguistic data in the form of distributional semantic vectors.”
Detecting Asymmetric Semantic Relations in Context: A Case-Study on Hypernymy Detection (2017, background): “Existing datasets for lexical entailment (Baroni and Lenci, 2011; Baroni et al., 2012; Kotlerman et al., 2010) have driven progress on the out of context task only, and are therefore insensitive to context changes.”
Building a shared world: mapping distributional to model-theoretic semantic spaces (2015, background): “Recent work in this area has even shown that entailment between explicit quantiﬁers can be modelled distributionally (Baroni et al., 2012).”
On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT (2020, background): “Additionally, our work ties into the rich history on modeling hypernymy in NLP systems (Lin, 1998; Weeds and Weir, 2003; Baroni et al., 2012; Rimell, 2014; Roller et al., 2014; Weeds et al., 2014; Shwartz et al., 2015; Vuli´c and Mrkˇsi´c, 2018) and evaluating distributional semantic models on…”
Siamese recurrent networks learn first-order logic reasoning and exhibit zero-shot compositional generalization (2019, unknown): “Related work Data-driven models have proven successful in various entailment recognition tasks (Baroni et al., 2012; Socher et al., 2012; Rocktäschel et al., 2014; Bowman et al., 2015b; Rocktäschel et al., 2015).”
Can recursive neural tensor networks learn logical reasoning? (2013, background): “…representations, but two recent projects have attempted to introduce vector representations into inference systems in other ways: Baroni et al. [12] have achieved limited success in building a classiﬁer to judge entailments between one-and two-word phrases (including some with quanti-ﬁers),…”
Do Supervised Distributional Methods Really Learn Lexical Inference Relations? (2015, methodology): “The various supervised meth-ods differ by the way they represent each candidate pair of words ( x, y ) : Baroni et al. (2012) use concatenation ~x ⊕ ~y , others (Roller et al., 2014; Weeds et al., 2014; Fu et al., 2014) take the vectors’ difference ~y − ~x , and more sophisticated representations,…”