No AI summary available for this article.
Why It Matters
Compositional generalisation has been divided into lexical and structural generalisation.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
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 dive...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.13144v1 · Indexed 7 days ago