← Search

Pu-Chin Chen

1 accepted papers

2021

A Simple and Effective Positional Encoding for Transformers

EMNLP 2021main

Transformer models are permutation equivariant. To supply the order and type information of the input tokens, position and segment embeddings are usually added to the input. Recent works proposed variations of positional encodings with relative position encodings achieving better performance. Our an…

Cited by 83SourcePDFScholar