Type Diversity Enables Transformers to Generalise Compositionally

2026-09-11

AI Summary

研究通过调整词汇和结构类型的多样性，探讨了Transformer在组合泛化上的表现，发现类型多样性对组合泛化的影响在词汇和结构上是相同的。

Abstract

Compositional generalisation has been divided into lexical and structural generalisation. Previous work has found that structural generalisation is harder than lexical for Transformers. We propose that this difference is not inherent to Transformers, but due to the high diversity of lexical types and low diversity of structural types in the specific datasets of these previous works. By type diversity we mean the number of different constructors of that type, instead of, for example, the specific word combinations that might populate the structure. To test this, we vary the amounts of type diversity of lexical and structural types in previously published datasets. We create linguistically diverse variants of the COGS and SLOG datasets using Grammatical Framework. We find that type diversity correlates with compositional generalisation equally in lexical and structural test cases, supporting our hypothesis. We note a contradiction with the proposition in previous work that compound divergence explains the difficulty in compositional generalisation tasks. We further investigate the effects of other dataset properties on compositional generalisation, such as the diversity of types other than the novel test structure, and surface properties of the logical semantics format.

Problem

• Compositional Generalisation
• Type Diversity
• Transformers

Innovation

• type diversity
• compositional generalisation
• Transformers
• lexical types
• structural types