Open devikasondhi opened 4 years ago
Probably yes! BUT: POS Taggers are either probabilistic models or rule-based methods and are therefore NEVER 100% accurate. Even modern models using contextualized word embeddings have some 5 - 10 % error rate on this Task :)
Hello,
Referring to the text sample
We will meet at eight o'clock on Thursday morning.
in POS.ipynb notebook, shouldn't the tokeno'clock
be tagged as an adverb instead of aNoun
, as can be verified with any standard English dictionary?