Measuring Semantic Similarity by Latent Relational Analysis

By Peter D. Turney. 2005

193 citations recorded by the source corpus.

This paper introduces Latent Relational Analysis (LRA), a method for measuring semantic similarity. LRA measures similarity in the semantic relations between two pairs of words. When two pairs have a high degree of relational similarity, they are analogous. For example, the pair cat:meow is analogous to the pair dog:bark. There is evidence from cognitive science that relational similarity is fundamental to many cognitive and linguistic tasks (e.g., analogical reasoning). In the Vector Space Model (VSM) approach to measuring relational similarity, the similarity between two pairs is calculated by the cosine of the angle between the vectors that represent the two pairs. The elements in the vectors are based on the frequencies of manually constructed patterns in a large corpus. LRA extends the VSM approach in three ways: (1) patterns are derived automatically from the corpus, (2) Singular Value Decomposition is used to smooth the frequency data, and (3) synonyms are used to reformulate word pairs. This paper describes the LRA algorithm and experimentally compares LRA to VSM on two tasks, answering college-level multiple-choice word analogy questions and classifying semantic relations in noun-modifier expressions. LRA achieves state-of-the-art results, reaching human-level performance on the analogy questions and significantly exceeding VSM performance on both tasks.

Subfields: Artificial Intelligence

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

Citations in the corpus

Efficient Estimation of Word Representations in Vector Space (2013, neutral): “In the future, it would be also interesting to compare our techniques to Latent Relational Analysis [27] and others.”
From Frequency to Meaning: Vector Space Models of Semantics (2010, methodology): “Turney (2005) used a pair–pattern matrix to classify noun compounds into semantic classes.”
SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals (2009, background): “at the second one; other researchers (Kim and Baldwin, 2005; Nakov and Hearst, 2008; Nastase et al., 2006; Turney, 2005; Turney and Littman, 2005) have used their class scheme and data set.”
AnalogySpace: Reducing the Dimensionality of Common Sense Knowledge (2008, background): “Turney (2005) creates a matrix using the co-occuring words as the rows and the context in which the words appear within a sentence as the columns.”
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).”
UTD: Determining Relational Similarity Using Lexical Patterns (2012, methodology): “In the vein of previous methods for determining relational similarity (Turney, 2011; Turney, 2008a; Turney, 2008b; Turney, 2005), we propose two approaches using patterns generated from the contexts in which the word pairs occur.”
Similarity of Semantic Relations (2006, methodology): “In this section, we explore connections between attributional and relational similarity.”
pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference (2018, methodology): “Mining Textual Patterns There is extensive literature on mining textual patterns to predict relations between words (Hearst, 1992; Snow et al., 2005; Turney, 2005; Riedel et al., 2013; Van de Cruys, 2014; Toutanova et al., 2015; Shwartz and Dagan, 2016).”
SemEval-2012 Task 2: Measuring Degrees of Relational Similarity (2012, background): “Nastase and Szpakowicz (2003) propose a two-level hierarchy for noun-modiﬁer relations, which has been widely used (Nakov and Hearst, 2008; Nastase et al., 2006; Turney and Littman, 2005; Turney, 2005).”