-1

For a Kaggle competition I would like to decontextualise a list of questions. One way I am planning to do it is to replace any noun representing a group of people with a placeholder.

Examples of such nouns are:

women males Muslims democrats conservatives racists feminists veterans vegans moguls Britons minorities Asians leaders

In this StackExchange I would like to find out where can I find a list of words that represent a group of people.

Proper nouns is not a big problem as the module I use (spaCy) can detect them as NORP (nationalities or religious or political groups) because of their capitalisation.

I hope we can get all the words that appear in a standard dictionary, especially those that end with -ist, -er and -an.

migrated from english.stackexchange.com Dec 14 '18 at 2:31

This question came from our site for linguists, etymologists, and serious English language enthusiasts.

  • Welcome HK Tong... minor point, a request for a resource like this actually goes to the meta version of this board. I've asked for a close vote to trigger a move. You can also repost directly there to move things along. – jimm101 Dec 12 '18 at 15:54
  • Do you want to decontextualize? "Why do so many conservatives hate women?" is a rather different question from "Why do so many conservatives hate communists?" – eyeballfrog Dec 12 '18 at 15:56
  • Thanks jimm101, please do, as I am new here I do not think I have meta privileges. Dear eyeballfrog, the two questions you have cited will indeed deserve different labels, and it is an example that I didn't think of. Nevertheless I hope to try out a new approach to the problem. – HK Tong Dec 12 '18 at 16:17
1

This kind of question turns out to have more traffic over at Stack Overflow.

It is a request for a software process to help with Named Entity Recognition (NER). Try asking there.

(as an aside, to hint towards possible answers informed by the linguistics you expected here, "any noun representing a group of people" almost sounds like any plural noun. Sure, you probably don't want 'ducks', but you know how they are).

But I've given you some extra keywords to help with your search. Off the top of my head I'm having a hard time expecting a word list with exactly the kinds of groups you're thinking of. With these sorts of tasks you very well may be successful generating that list yourself and providing it to the community (you already have a good start).

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .