"Attention Weights in Transformer NMT Fail Aligning Words Between Sequences ..."

Javier Ferrando, Marta R. Costa-jussà (2021)

> Home

Details and statistics

DOI: 10.18653/V1/2021.FINDINGS-EMNLP.39

access: open

type: Conference or Workshop Paper

metadata version: 2022-01-20

- view
  - electronic edition via DOI (open access)
  - electronic edition @ aclanthology.org (open access)
  authority control:
- export record
  dblp key:
  - conf/emnlp/FerrandoC21
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/emnlp/FerrandoC21
Javier Ferrando, Marta R. Costa-jussà:
Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions. EMNLP (Findings) 2021: 434-443

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.