Looks like a new trained model has forgotten the old entities

[ines (Ines Montani)]

How many examples did you collect and how many entities did you label in total? Do they overlap with existing types? And how did you train the model? It seems like your model has learned that "everything is MED now" – so if you want to prevent it from "forgetting" previously predicted labels, you usually want to also include examples of what the model previously got right, not just the new annotations. Alternatively, you can train a new model from scratch using the labels you need, so you don't have to deal with the side-effects of the existing weights.

You can find more details on preventing "catastrophic" forgetting here:

New entity model ruins other entities

I’m trying to train a new entity of type “Technology”. I started with some seed terms, created patterns and annotated ~300 examples. Then I batch-trained them with en_core_web_lg as a baseline model. Although I don’t have a lot of annotations yet, I wanted to see how the model is doing so far. It seems that the model mislabels a lot of entities and tends to label non-entities as WORK_OF_ART: import spacy nlp = spacy.load('tech-model') doc = nlp('Blockchain is a kind of technology') [(ent.tex…

Mixing in gold data to avoid catastrophic forgetting

I have a question about how to best incorporate original training data to avoid catastrophic forgetting. I’ve been tweaking spaCy NER’s GPE tag to better pick up multi-word or hyphenated place names (which come up a lot in Spanish and Arabic names) and on some kinds of short text. After a thousand examples or so, the quality on those improves, but really falls apart on other place names. I’ve licensed the OntoNotes corpus and would like to be able to use its annotations to remind spaCy what othe…