search

lfoppiano / grobid-quantities

GROBID extension for identifying and normalizing physical quantities.
https://grobid-quantities.readthedocs.io
Apache License 2.0
72 stars 24 forks source link

Use the grobid sentence segmenter #115

Closed lfoppiano closed 2 years ago

lfoppiano commented 3 years ago

Right now we are using the clearnlp sentence segmenter. We could replace this with the internal grobid sentence segmentation.
We could implement the segmentation also in the quantityparser to reduce the impact of #87 (although we could not guarantee to remove completely this glitch)

This would require the release of grobid 0.6.2

lfoppiano commented 2 years ago

Now grobid-quantities uses OpenNLP sentence segmenter for the quantified object. Since the segmentation in the quantity parser would requires changes in the training data (from paragraphs to sentence), this will be addressed in the future #140