Combining Subword Representations into Word-level Representations in the Transformer Architecture

ACL 2020 Noe CasasMarta R. Costa-juss{\`a}Jos{\'e} A. R. Fonollosa

In Neural Machine Translation, using word-level tokens leads to degradation in translation quality. The dominant approaches use subword-level tokens, but this increases the length of the sequences and makes it difficult to profit from word-level information such as POS tags or semantic dependencies... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper