A Simple, Similarity-based Model for Selectional Preferences

By K. Erk. 2007

161 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

Probing for semantic evidence of composition by means of simple classification tasks (2016, methodology): “Possible approaches to estimating plausibility without human annotation include using n-gram statistics on simple argument/predicate combinations (Rashkin et al., 2016) or making use of se-lectional preference modeling (Resnik, 1996; Erk, 2007; S´eaghdha, 2010).”
From Frequency to Meaning: Vector Space Models of Semantics (2010, positive): “Erk (2007) presented a system in which a word–context frequency matrix was used to improve the performance of semantic role labeling. Pennacchiotti, Cao, Basili, Croce, and Roth (2008) show that word–context matrices can reliably predict the semantic frame to which an unknown lexical unit refers, wi”
A Structured Vector Space Model for Word Meaning in Context (2008, methodology): “We use a simple, knowledge-lean representation for selectional preferences inspired by Erk (2007), who models selectional preference through similarity to seen ﬁller vectors ~v a : We compute the selectional preference vector for word b and relation r as the weighted centroid of seen ﬁller vectors…”
Distributional Memory: A General Framework for Corpus-Based Semantics (2010, neutral): “Our method is essentially the same, save for implementation and parameter choice details, as the one proposed by Pad´o, Pad´o, and Erk (2007), in turn inspired by Erk (2007).”
Measuring the Evolution of a Scientific Field through Citation Frames (2018, background): “selectional preferences reflecting expectations for predicate arguments (Erk, 2007).”
Estimating Linear Models for Compositional Distributional Semantics (2010, methodology): “Selectional preferences are computed as in Erk (2007).”
Special Issue Introduction: Semantic Role Labeling: An Introduction to the Special Issue (2008, unknown): “Performance can be divided into two components: (1) the precision, recall, and F 1 of unlabeled arguments, measuring the accuracy of the system at segmenting the sentence; and (2) the classiﬁcation accuracy of assigning semantic roles to the arguments that have been correctly identiﬁed.”
Web-Scale Distributional Similarity and Entity Set Expansion (2009, background): “…2003), word sense disambiguation (Yuret and Yatbaz 2009), context-spelling correction (Jones and Martin 1997), fact extraction (Pa ş ca et al. 2006), semantic role labeling (Erk 2007), and applications in IR such as query expansion (Cao et al. 2008) and textual advertising (Chang et al. 2009).”
From Word to Sense Embeddings: A Survey on Vector Representations of Meaning (2018, methodology): “…their eﬀectiveness in NLP tasks such as information extraction (Laender, Ribeiro-Neto, da Silva, & Teixeira, 2002), semantic role labeling (Erk, 2007), word similarity (Radinsky, Agichtein, Gabrilovich, & Markovitch, 2011), word sense disambiguation (Navigli, 2009) or spelling correction…”
Latent Variable Models of Selectional Preference (2010, background): “(2007), a refinement of Erk (2007), is a non-probabilistic method that smooths predicate-argument counts with counts for other observed arguments of the same predicate, weighted by the similarity between arguments.”
Sketch Algorithms for Estimating Point Queries in NLP (2012, methodology): “The pseudo-words are a common way to evaluate selectional preferences models (Erk, 2007; Bergsma et al., 2008) that”
Multi-Prototype Vector-Space Models of Word Meaning (2010, methodology): “Exemplar models have been previously used for lexical semantics problems such as selectional preference (Erk, 2007) and thematic fit (Vandekerckhove et al.”