Directional distributional similarity for lexical inference

By Lili Kotlerman, Ido Dagan, Idan Szpektor, Maayan Zhitomirsky-Geffet. 2010

244 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology, 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 Artificial Intelligence

In Molecular Biology

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions (2014, methodology): “More recently, asymmetric similarities have been proposed as more suitable for semantic inference tasks such as entailment (Weeds and Weir, 2003; Szpektor and Dagan, 2008; Clarke, 2009; Kotlerman et al., 2010).”
Linguistic Regularities in Sparse and Explicit Word Representations (2014, background): “…been extensively studied in the NLP literature (see (Tur-ney and Pantel, 2010; Baroni and Lenci, 2010) and the references therein), and are known to exhibit a large extent of attributional similarity (Pereira et al., 1993; Lin, 1998; Lin and Pantel, 2001; Sahlgren, 2006; Kotlerman et al., 2010).”
Entailment above the word level in distributional semantics (2012, methodology): “In particular, Kotlerman et al. (2010) carefully crafted the balAPinc measure (see Section 3.5 below).”
Learning Semantic Hierarchies via Word Embeddings (2014, methodology): “We re-implement two previous distributional methods M balApinc (Kotlerman et al., 2010) and M invCL (Lenci and Benotto, 2012) in the Baidubaike corpus.”
Distributional Models of Word Meaning (2018, background): “Each measure exploits some variation of the DH on the basis of either feature inclusion (Kotlerman et al. 2010, Lenci & Benotto 2012) or feature informativeness (Rimell 2014, Santus et al. 2014a), aiming to capture the fact that hypernyms are semantically broader than hyponyms.”
Efficient Search for Transformation-based Inference (2012, methodology): “We employed a comprehensive set of knowledge resources (available in B IU T EE ’s web site): WordNet (Fellbaum, 1998), Directional similarity (Kotlerman et al., 2010), DIRT (Lin and Pantel, 2001) and generic syntactic rules.”
Context Mover's Distance & Barycenters: Optimal transport of contexts for building representations (2018, background): “The early unsupervised approaches for this task exploited different linguistic properties of hypernymy (Weeds & Weir, 2003; Kotlerman et al., 2010; Santus et al., 2014; Rimell, 2014).”
Frege in Space: A Program of Compositional Distributional Semantics (2014, background): “Kotlerman et al. (2010) and others use DSMs to predict lexical entailment (discovering whether the concept denoted by one word implies the one denoted by another; for example, dog entails animal).”
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.”
Focused Entailment Graphs for Open IE Propositions (2014, methodology): “We used various metrics to measure different types of similarities between each component pair, including: cosine similarity, Lin’s similarity (1998), inclusion (Weeds and Weir, 2003), average precision, and balanced average precision (Kotlerman et al., 2010).”
Do Supervised Distributional Methods Really Learn Lexical Inference Relations? (2015, background): “Many unsupervised distributional methods of recognizing lexical inference replace cosine similarity with an asymmetric similarity function (Weeds and Weir, 2003; Clarke, 2009; Kotlerman et al., 2010; Santus et al., 2014).”
A Natural Proof System for Natural Language (2017, background): “Kruszewski and Baroni (2015) tried to model (in)compatible words while the others including Kotlerman et al. (2010); Levy et al. (2015); Shwartz et al. (2016) focused on the hypernymy/entailment relation.”