A Uniform Approach to Analogies, Synonyms, Antonyms, and Associations

Abstract

Recognizing analogies, synonyms, antonyms, and associations appear to be four distinct tasks, requiring distinct NLP algorithms. In the past, the four tasks have been treated independently, using a wide variety of algorithms. These four semantic classes, however, are a tiny sample of the full range of semantic phenomena, and we cannot afford to create ad hoc algorithms for each semantic phenomenon; we need to seek a unified approach. We propose to subsume a broad range of phenomena under analogies. To limit the scope of this paper, we restrict our attention to the subsumption of synonyms, antonyms, and associations. We introduce a supervised corpus-based machine learning algorithm for classifying analogous word pairs, and we show that it can solve multiple-choice SAT analogy questions, TOEFL synonym questions, ESL synonym-antonym questions, and similar-associated-both questions from cognitive psychology.

arXiv commentrelated work available at http://purl.org/peter.turney/

References in corpus (3)

• Using Information Content to Evaluate Semantic Similarity in a Taxonomy
• Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy
• Combining Independent Modules to Solve Multiple-choice Synonym and Analogy Problems

Cited by in corpus (9)

• From Frequency to Meaning: Vector Space Models of Semantics
• Text Relatedness Based on a Word Thesaurus
• Analogical Reasoning on Chinese Morphological and Semantic Relations
• BagPack: A general framework to represent semantic relations
• Development and Evaluation of a Personalized Computer-aided Question Generation for English Learners to Improve Proficiency and Correct Mistakes
• Bringing personalized learning into computer-aided question generation
• Computing Lexical Contrast
• CogALex-V Shared Task: ROOT18
• Analogy perception applied to seven tests of word comprehension