Timeline for Fastest way for 1 vs all lookup on embeddings
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 16, 2020 at 15:57 | comment | added | Isbister | No worries. I am using BERT as my language model, all pre-computed embeddings and new embeddings are from the same BERT model. Do you have any additional ideas of best practices here. If so could you update your answer and I perhaps can accept it! Thanks | |
| Mar 16, 2020 at 14:44 | comment | added | Edoardo Guerriero | Sorry, I missed the word 'sentence'. What model are you using to produce them? Bert, elmo or just average of pre-trained embeddings? And are the other pre-computed embedding also coming from the same model? It's relevant cause you might have an alignment problem if the vectors come from different sources, at that point the whole comparison would be meaningless | |
| Mar 16, 2020 at 8:32 | comment | added | Isbister | Thanks, I am aware of this approach when using word level embeddings. But I have context embeddings created by the whole sentence! I could store each sentence to a id instead of a word in the standard format embeddings file. But not entirely sure how I could use the similar_by_word("This is a sentence") method, any ideas? | |
| Mar 15, 2020 at 23:48 | history | answered | Edoardo Guerriero | CC BY-SA 4.0 |