Login / Signup

Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models.

Shun KiyonoSho TakaseJun SuzukiNaoaki OkazakiKentaro InuiMasaaki Nagata
Published in: BlackboxNLP@EMNLP (2018)
Keyphrases
  • low complexity
  • probabilistic model
  • semi supervised
  • unsupervised learning
  • information theoretic
  • distributed video coding