1
$\begingroup$

I tried finding about exception lists in wordnet lemmatizers. "Morphy() uses inflectional ending rules and exception lists to handle different possibilities" which I read from http://www.nltk.org/howto/wordnet.html . Can you explain what is an exception list. Thank you.

$\endgroup$
2
$\begingroup$

The exception list files are used to help the processor find base forms from 'irregular inflections' according to the man page. They mean that some words, when plural or a different tense, can't be algorithmically processed to find the base/root word. More details can be found in the morphy man. I'm not a language processing expert, but this is likely a result of English words that 'break the rules'. If you think about the code like a human trying to learn English: the student learns rules to use (algorithm) and then has to memorize exceptions for the rules (exception lists). An over-simplified analogy that does not involve endings/conjugation would a spell checking program. An algorithm might check for 'i before e, except after c' but would first have to check the word against an exception list to make sure it isn't 'weird' or 'caffeine' - please don't start a linguistics fight about this rule, I am not commenting on the validity of it/that's not the point I'd like to make.

| improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.