Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding

Daichi Hayakawa; Issei Sato

doi:10.18653/v1/2025.acl-long.1488

ScienceGate Book Chapters

JOURNAL ARTICLE

Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding

Daichi Hayakawa Issei Sato

Year: 2025 Pages: 30777-30834

DOI: 10.18653/v1/2025.acl-long.1488

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Transformer Encoding (memory) Natural language processing Artificial intelligence Speech recognition Pattern recognition (psychology) Engineering Electrical engineering Voltage

Metrics

Cited By

0.00

FWCI (Field Weighted Citation Impact)

Refs

0.12

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Topics

Speech Recognition and Synthesis

Physical Sciences → Computer Science → Artificial Intelligence

Robotics and Automated Systems

Physical Sciences → Engineering → Control and Systems Engineering

Speech and dialogue systems

Physical Sciences → Computer Science → Artificial Intelligence

Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding

Metrics

Topics

Related Documents

Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding

Applying Positional Encoding to Enhance Vision-Language Transformers

POSITIONAL ENCODING FOR TRANSFORMERS

HDTSLR: A Framework Based on Hierarchical Dynamic Positional Encoding for Sign Language Recognition

Multiresolution graph transformers and wavelet positional encoding for learning long-range and hierarchical structures