I am doing some coding to retrieve the dictionary forms of Russian words. It generally seems to be working reasonably well, but for the word "её", it leaves it unchanged instead of changing it to "она". I've tried two different programmes with similar results.

In the first (pymystem3), if I try it with only the word "её", it does give me the correct "она", but if it's in a sentence, it returns "ее".

In the second (pymorphy2), it gives "её" on both occasions. If I try the same with e.g. "его", I get the correct "он".

It made me wonder if this is some kind of a glitch with the programmes I'm using or if I'm missing something about the word "её"?

  • 6
    Do you mean you think она is the only correct dictionary form of её? In fact, её has 2 meanings, there are 2 homonyms: 1. Genitive and Accusative case of the 3rd p. feminine personal pronoun она (Я видел её - “I saw her”) – here the dictionary form is она; 2. 3rd p. sg. feminine possessive pronoun, indeclinable (её отец - “her father”) – here the dictionary form is её. To tell the two homonyms from each other one needs to do syntactic analysis of the text, mere search through a word-list is not enough. – Yellow Sky Jul 30 at 7:16
  • 4
    Besides, её is often written as ее, in the standard Russian orthography the two dots over ё is optional and can be freely omitted. A good dictionary will have the dots, but you know, things happen. – Yellow Sky Jul 30 at 7:18
  • Thanks, @YellowSky, I forgot about the second dictionary form! – MeL Jul 30 at 7:40

Your Answer

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

Browse other questions tagged or ask your own question.