The Latent Relation Mapping Engine: Algorithm and Experiments

TL;DR

The paper introduces LRME, an algorithm that automatically discovers semantic relations from text to perform analogy mapping, achieving human-level accuracy without hand-coded representations.

Contribution

LRME combines SMT and LRA ideas to automatically learn relations, removing the need for hand-coded representations in analogy-making.

Findings

LRME achieves human-level performance on 20 analogy problems.

Compared to alternatives, LRME outperforms in analogy mapping accuracy.

LRME effectively uses large text corpora to discover semantic relations.

Abstract

Many AI researchers and cognitive scientists have argued that analogy is the core of cognition. The most influential work on computational modeling of analogy-making is Structure Mapping Theory (SMT) and its implementation in the Structure Mapping Engine (SME). A limitation of SME is the requirement for complex hand-coded representations. We introduce the Latent Relation Mapping Engine (LRME), which combines ideas from SME and Latent Relational Analysis (LRA) in order to remove the requirement for hand-coded representations. LRME builds analogical mappings between lists of words, using a large corpus of raw text to automatically discover the semantic relations among the words. We evaluate LRME on a set of twenty analogical mapping problems, ten based on scientific analogies and ten based on common metaphors. LRME achieves human-level performance on the twenty problems. We compare LRME with a variety of alternative approaches and find that they are not able to reach the same level of performance.