I tried to add an extra dimension to the Huggingface pre-trained BERT tokenizer. The extra column represents the extra label. For example, if the original embedding of the word “dog” was [1,1,1,1,1,1,1], then I might add a special column with index 2 to represent ‘noun’. Thus, the new embedding beco…

How to concatenate the word embedding for special tokens and words

xuan4470 June 13, 2021, 8:00am 2

Topic		Replies	Views
How to train the embedding of special token? Intermediate	1	2420	October 17, 2021
Is it OK to get word embedding without adding special tokens? Beginners	3	995	April 15, 2023
Process to adding new tokens to a corpus and subsequently training the corresponding word embeddings Beginners	0	2723	April 21, 2021
Adding a new mask_token for BERT-like models/tokenizers Intermediate	0	357	May 26, 2023
How to create a Huggingface tokenizer from a non-Huggingface tokenizer? 🤗Tokenizers	0	380	May 4, 2021