On decoding strategies for neural text generators

HIGHLIGHTS

• who: Gian Wiher et al. from the ETH Zuu0308rich, Switzerland have published the Article: On Decoding Strategies for Neural Text Generators, in the Journal: (JOURNAL)
• what: Empirically, the authors compare strategy performance on several axes, taxonomizing methods into groups such as deterministic and stochastic, to understand the importance of various strategy attributes for quantifiable properties of text. The authors report the ROUGE-L measure, which is based on longest common subsequences between candidate and reference. While the authors provide some results for the former set of metrics, the authors focus largely on the latter set . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.