Part-of-speech Tagging

[Natasha N]

On the preparation video on ‘Letter to Sound’, Simon mentioned that POS works best when used with well developed languages. But I was wondering what this meant. I thought that a language would not be in existence if it was not well developed in morphology, syntax etc. Is the concept of a well developed language in speech processing/informatics different to one in linguistics?

[Simon]

“Well developed” meant in terms of linguistic knowledge and resources. Specifically, because POS tagging is performed using supervised machine learning, we need lots of accurately labelled (i.e., hand-tagged) data on which to train our tagger.

[Author]

Posts