Spacy detects the entities using its predefined algorithm. It parses tokens in text considering position of tokens with respect to tokens surrounding it. It also takes into consideration the POS tagging for these tokens.

However, I believe it misses the position of tokens above and below (For example in a tabular data) or it also misses few properties of text like if it is underline etc. This statement is based on my understanding. Please correct me if I am wrong in these.

Now the question is, can such properties be taken into consideration while doing training and prediction of entities? I have seen Extension Attributes, but these do not play role during training and prediction but work as meta data.


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.