Novel positional encodings to enable tree-based transformers

Vighnesh Shiv, Chris Quirk

Oct-2-2025, 23:06:15 GMT–Neural Information Processing Systems

Motivated by this property, we propose a method to extend transformers to tree-structured data, enabling sequence-to-tree, tree-to-sequence, and tree-to-tree mappings.

artificial intelligence, machine learning, natural language, (19 more...)

Neural Information Processing Systems

Oct-2-2025, 23:06:15 GMT

Conferences PDF

Country:
- Asia > Middle East
  - Jordan (0.04)
- Europe
  - Germany > Berlin (0.04)
  - United Kingdom > England
    - Greater London > London (0.04)
- North America
  - Canada (0.04)
  - United States
    - California > San Mateo County
      - Menlo Park (0.04)
    - Louisiana > Orleans Parish
      - New Orleans (0.04)
    - New Jersey (0.04)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning > Neural Networks
    - Deep Learning (0.49)
  - Natural Language
    - Grammars & Parsing (0.96)
    - Machine Translation (0.95)
  - Representation & Reasoning (1.00)

Duplicate Docs Excel Report

Title
Novel positional encodings to enable tree-based transformers

Similar Docs Excel Report more

Title	Similarity	Source
None found