You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
KMeansSummarizer's .predict() accepts only Doc object, however when using KMeans normally (aka with __ call __), ExtractiveSummarizer gets Doc's sentences first and passes those to predict, which breaks KMeans when used to summarize and not to score.
The text was updated successfully, but these errors were encountered:
We have significantly standardized our summarizers (specifically
cluster based ones)
Summarizers now allow following parameter types on `predict` and
`__call__` functions:
Doc
List[Sentences]
List[str] (each element is taken as a sentence)
Reference [commit: 8b1cfe8]
KMeansSummarizer's .predict() accepts only Doc object, however when using KMeans normally (aka with __ call __), ExtractiveSummarizer gets Doc's sentences first and passes those to predict, which breaks KMeans when used to summarize and not to score.
The text was updated successfully, but these errors were encountered: