entity-fishing icon indicating copy to clipboard operation
entity-fishing copied to clipboard

Support acronyms

Open kermitt2 opened this issue 7 years ago • 4 comments

Detect acronyms introduced (explicitly or not) in a document , and maintain them as possible mention in the current document.

Example: frequent for name of species (C. Lupus, C. n. gregoryi), Cigarette smoke (CS)-induced

kermitt2 avatar Jun 29 '17 07:06 kermitt2

Done but it needs further testing.

kermitt2 avatar Oct 20 '17 11:10 kermitt2

Some tests for recognizing acronyms were done for the text and also Pdf disambiguation process.

  1. For the text disambiguation process with the text of PubMed_2, the result shows the recognition of all the explicitly acronym Cigarette smoke (CS) despite of a problem that the Type of the acronym can be different.
screen shot 2018-03-20 at 16 09 25

Another issue will be opened related to this problem.

  1. For the Pdf disambiguation service, this issue also deals with other issues #69 about generating layout tokens for acronyms.

tantikristanti avatar Mar 20 '18 15:03 tantikristanti

This issue is closed and another issue #74 is opened.

tantikristanti avatar Mar 20 '18 15:03 tantikristanti

I reopen it because there are still quite a lot of cases not supported (mixture of upper/lower cases in aconym, special sombols like -) and issue #74 is not specific to acronyms.

kermitt2 avatar Mar 20 '18 15:03 kermitt2