search

lephong / mulrel-nel

named entity linking with latent relations
Apache License 2.0
172 stars 36 forks source link

What modifications should be made to apply it to other languages? #6

Open DexterZeng opened 6 years ago

DexterZeng commented 6 years ago

Hi, thank you for sharing the codes.

I successfully ran the codes according to the instructions. However, currently I want to apply the method on a Chinese EL dataset. I think it is not hard to change to original dataset format to the format used in this experiment. Nevertheless, I wonder what other things I need to change/add to run it? I already have the Chinese word/entity embeddings, frequency dictionary for popularity scores (p_e_m) and candidate entities for mentions.

Also, I am not sure about several places. Could you kindly explain what's the difference between secondary local context and the original context and why do they use different word embeddings? And what are abstract_word_entity.py used for?

Thank you for your time and I look forward to your reply. Weixin.

liqijiaLQJ commented 3 years ago

Hi, thank you for sharing the codes.

I successfully ran the codes according to the instructions. However, currently I want to apply the method on a Chinese EL dataset. I think it is not hard to change to original dataset format to the format used in this experiment. Nevertheless, I wonder what other things I need to change/add to run it? I already have the Chinese word/entity embeddings, frequency dictionary for popularity scores (p_e_m) and candidate entities for mentions.

Also, I am not sure about several places. Could you kindly explain what's the difference between secondary local context and the original context and why do they use different word embeddings? And what are abstract_word_entity.py used for?

Thank you for your time and I look forward to your reply. Weixin.

Hi.Have you solved this problem？(what's the difference between secondary local context and the original context and why do they use different word embeddings) thank you.

mawuuu commented 3 years ago

Hi @DexterZeng,

Might I ask what code you ran to get Chinese word/entity embeddings, frequency dictionary for popularity scores (p_e_m) and candidate entities for mentions. (And if possible, would you be willing to share the code with me) In particular, I am interested in generating popularity scores (p_e_m) and candidate entities for mentions in danish.

Best regards and thanks in advance, M. Wu

DexterZeng commented 3 years ago

@liqijiaLQJ @mawuuu Hi, thank you for your questions but I have not continued with the exploration since I did not receive any feedback. You may want to resort to others for possible solutions. Good luck!

liqijiaLQJ commented 3 years ago

@DexterZeng Thank you for your reply. Best regards.