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

TL;DR

This paper proposes a unified supervised machine learning approach to classify and solve various semantic tasks like analogies, synonyms, antonyms, and associations, demonstrating its effectiveness across multiple standardized tests.

Contribution

It introduces a single supervised learning algorithm that subsumes multiple semantic phenomena, reducing the need for task-specific algorithms.

Findings

Successfully solves SAT analogy questions

Accurately classifies TOEFL synonym questions

Performs well on cognitive psychology association tasks

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.