Difference between revisions of "User talk:Francis Tyers/Apertium 4"
Jump to navigation
Jump to search
(Created page with " :: Tanmai Khanna (talk) Isn't that also one of the disadvantages of neural models with strong language models that prefer flu...") |
(No difference)
|
Latest revision as of 16:14, 24 June 2020
- Tanmai Khanna (talk) Isn't that also one of the disadvantages of neural models with strong language models that prefer fluency over adequacy? At least in RBMT we can guarantee not giving up adequacy for fluency.
- Yes, there is a trade off, but I'd prefer the output to be adequate or fluent, but not neither adequate nor fluent. -Francis Tyers (talk) 16:14, 24 June 2020 (UTC)
