Novel positional encodings to enable tree-based transformers

Vighnesh Shiv, Chris Quirk

Neural Information Processing Systems 

Motivated by this property, we propose a method to extend transformers to tree-structured data, enabling sequence-totree, tree-to-sequence, and tree-to-tree mappings. Our approach abstracts the transformer'ssinusoidal positional encodings, allowing ustoinstead useanovel positional encoding scheme to represent node positions within trees.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found