search

kermitt2 / grobid

A machine learning software for extracting information from scholarly documents
https://grobid.readthedocs.io
Apache License 2.0
3.59k stars 459 forks source link

Extracting Citation Sentences Related to Reference Using Grobid #1145

Closed phat-innomizetech closed 3 months ago

phat-innomizetech commented 3 months ago

Hi everyone, I am using Grobid to extract citations from a document PDF. Okay, it is working well, but I want Grobid to also provide citation sentences related to the citations found. Does anyone have a solution to help me achieve this?

Thank you.

kermitt2 commented 3 months ago

Hello @phat-innomizetech Use the available parameter segmentSentences when using the service. You can then extract the sentence containing the citation with your favorite XML parser. You can choose between two sentence segmenter implementations, see https://grobid.readthedocs.io/en/latest/Configuration/#language-processing-implementation