UTD: Determining Relational Similarity Using Lexical Patterns

15 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.

Multi-Relational Latent Semantic Analysis (2013, neutral): “1) UTDNB (Rink and Harabagiu, 2012) 38.”
Question Answering Using Enhanced Lexical Semantic Models (2013, result): “In comparison, the previous best system (Rink and Harabagiu, 2012) in the task only reaches ρ = 0 .”
Linguistic Regularities in Continuous Space Word Representations (2013, background): “Sur-prisingly, we found that even though the RNN vec-749 (Rink and Harabagiu, 2012).”
SensEmbed: Learning Sense Embeddings for Word and Relational Similarity (2015, methodology): “We also report results for UTD-NB and UTD-SVM (Rink and Harabagiu, 2012), which rely on lexical pattern classiﬁcation based on Na¨ıve Bayes and Support Vector Machine classiﬁers, respectively.”
Quantifying Similarity between Relations with Fact Distribution (2019, methodology): “For identifying correlation and distinction between different semantic relations so as to support learning semantic similarity, various methods have attempted to measure relational similarity (Turney, 2005, 2006; Zhila et al., 2013; Pedersen, 2012; Rink and Harabagiu, 2012; Mikolov et al., 2013b,a).”
Combining Heterogeneous Models for Measuring Relational Similarity (2013, methodology): “Indeed, by mining lexical patterns from a large corpus, the UTD system (Rink and Harabagiu, 2012) managed to outperform other participants in the SemEval-2012 task of measuring relational similarity.”