'Mapping from fine-grained POS tags to coarse-grained tags tags
I have a bunch of documents already POS tagged with fine-grained POS tags, specific to English.
I would like to map those tags to coarse-grained tags that more universal across different languages.
Is there a mapping defined in spacy for that?
For instance, something that maps all the following fine-grained tags to NOUN.
"NN": "noun, singular or mass",
"NNP": "noun, proper singular",
"NNPS": "noun, proper plural",
"NNS": "noun, plural",
I know that spacy can tag document with both types of tags, but I don't want to re-tag the document again.
Solution 1:[1]
spaCy is already doing what you describe in the pretrained models using an AttributeRuler in the pipeline. I would recommend you look at the AttributeRuler documentation.
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 | polm23 |