Out-of-band Language Modelling
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Emli-Mari Nel.
Language modelling techniques depend upon a large body of training text to achieve good predictive performance. When the training text differs from the test text in vocabulary or writing style, predictive performance degrades substantially. In this talk, various techniques which can be applied to limit this degradation will be described, with lots of performance figures. (No new techniques will be presented.)
This talk is part of the Inference Group series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|