POS-tagging

parent:
linguistics

Related:


Overview

It can do 1-shot POS tagging, although not 100%. Will have gists up in a second but eating lunch and breaking colab.

In the meantime,

1-shot POS tagging

Penn Treebank

Using NLTK's treebak, you can give a single example and it generally gets most of the tags right meaning it's probably picked it up somewhere. There may be a zero-shot method of getting it but so far it hasn't been found.

Sentence: 'Pierre Vinken , 61 years old , will join the board as a nonexecutive director Nov. 29 .'
Output:'Pierre:NNP Vinken:NNP ,:, 61:CD years:NNS old:JJ ,:, will:MD join:VB the:DT board:NN as:IN a:DT nonexecutive:JJ director:NN Nov.:NNP 29:CD .:.'
Sentence: ""We have no useful information on whether users are at risk , " said *T*-1 James A. Talcott of Boston 's Dana-Farber Cancer Institute ."
Output:[EOP] '"We:NNP have:VBP no:DT useful:JJ information:NN on:IN whether:IN users:NNS are:VBP at:IN risk:NN :, ":CC said:VBD *T*-1:NNP James:NNP A.:NNP Talcott:NNP of:IN Boston:NNP 's:IN Dana-Farber:NNP Cancer:NNP Institute:NNP .:.'

***DATASET ANSWER***
Output: "``:`` We:PRP have:VBP no:DT useful:JJ information:NN on:IN whether:IN users:NNS are:VBP at:IN risk:NN ,:, '':'' said:VBD *T*-1:-NONE- James:NNP A.:NNP Talcott:NNP of:IN Boston:NNP 's:POS Dana-Farber:NNP Cancer:NNP Institute:NNP .:."
Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License