Characterising Measures of Lexical Distributional Similarity

By Julie Weeds, David J. Weir, Diana McCarthy. International Conference on Computational Linguistics, 2004

313 citations recorded by the source corpus.

This work investigates the variation in a word's distributionally nearest neighbours with respect to the similarity measure used. We identify one type of variation as being the relative frequency of the neighbour words with respect to the frequency of the target word. We then demonstrate a three-way connection between relative frequency of similar words, a concept of distributional gnerality and the semantic relation of hyponymy. Finally, we consider the impact that this has on one application of distributional similarity methods (judging the compositionality of collocations).

View Paper: https://www.semanticscholar.org/paper/527eb9c939801f1edcedace66eff7bbc02f74e80

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

Finding Predominant Word Senses in Untagged Text (2004, background): “We want to investigate the effect of frequency and choice of distributional similarity measure (Weeds et al., 2004).”
Context-theoretic Semantics for Natural Language: an Overview (2009, background): “Our notion of entailment is based on the concept of distributional generality (Weeds et al., 2004), a generalisation of the distributional hypothesis of Harris (1985), in which it is assumed that terms with a more general meaning will occur in a wider array of contexts, an idea later developed by…”
The Distributional Inclusion Hypotheses and Lexical Entailment (2005, methodology): “The most widely used association weight function is (point-wise) Mutual Information ( MI ) (Church and Hanks, 1990; Lin, 1998; Dagan, 2000; Weeds et al., 2004).”
Directional distributional similarity for lexical inference (2010, methodology): “Geﬀet and Dagan (2005) extended the rationale of Weeds et al. (2004) to the lexical entailment setting.”
Schema and ontology matching with COMA++ (2005, unknown): “those of [2] and [12].”
Learning Semantic Hierarchies via Word Embeddings (2014, background): “Besides Kotlerman et al. (2010) and Lenci and Benotto (2012), other researchers also propose directional distributional similarity methods (Weeds et al., 2004; Geffet and Dagan, 2005; Bhagat et al., 2007; Szpektor et al., 2007; Clarke, 2009).”
Distributional Models of Word Meaning (2018, background): “Weeds et al. (2004) evaluated the effects of various measures on a word’s distributional neighbors.”
Entailment above the word level in distributional semantics (2012, background): “On the other hand, recent studies (Geffet and Dagan, 2005; Kotlerman et al., 2010; Weeds et al., 2004) have pursued the intuition that entailment is the asymmetric ability of one term to “substitute” for another.”
From Frequency to Meaning: Vector Space Models of Semantics (2010, background): “In one experiment on determining the compositionality of collocations, high-frequency sensitive measures outperformed the other classes (Weeds et al., 2004).”