Analogy perception applied to seven tests of word comprehension

TL;DR

This paper introduces PairClass, an algorithm that automatically recognizes lexical analogies from raw text data using high-level perception, achieving competitive results across seven tests of word comprehension.

Contribution

It presents a novel, uniform machine learning approach for analogy perception that works across diverse word comprehension tests without manual high-level representations.

Findings

Achieved competitive results on seven tests of word comprehension.

First approach to handle such a range of analogy perception tasks uniformly.

Demonstrated effectiveness of high-level perception in analogy recognition.

Abstract

It has been argued that analogy is the core of cognition. In AI research, algorithms for analogy are often limited by the need for hand-coded high-level representations as input. An alternative approach is to use high-level perception, in which high-level representations are automatically generated from raw data. Analogy perception is the process of recognizing analogies using high-level perception. We present PairClass, an algorithm for analogy perception that recognizes lexical proportional analogies using representations that are automatically generated from a large corpus of raw textual data. A proportional analogy is an analogy of the form A:B::C:D, meaning "A is to B as C is to D". A lexical proportional analogy is a proportional analogy with words, such as carpenter:wood::mason:stone. PairClass represents the semantic relations between two words using a high-dimensional feature vector, in which the elements are based on frequencies of patterns in the corpus. PairClass recognizes analogies by applying standard supervised machine learning techniques to the feature vectors. We show how seven different tests of word comprehension can be framed as problems of analogy perception and we then apply PairClass to the seven resulting sets of analogy perception problems. We achieve competitive results on all seven tests. This is the first time a uniform approach has handled such a range of tests of word comprehension.