Named Entity Recognition: fine-tune or create new model?

Jungroo-AI released ReDefiNER, an Apache 2.0-licensed 0.8B-parameter named-entity-recognition model that extracts entity types defined in a plain-English rulebook rather than requiring relabeling and retraining, and runs on a CPU. The model's README shows that adding a single line to change "$120" to "under $120" required no retraining, and the author notes ReDefiNER scores a few points below large API models on public benchmarks, recommending labeled data be used as a test set on the user's own text.

Another option now: a model that reads the entity types from its input, so adding PRICE and PRODUCT means describing them instead of relabelling and retraining. I built one, ReDefiNER GitHub - Jungroo-AI/redefiner: A 0.8B model that extracts the entities you define in a plain-English rulebook. It runs on a CPU and is free under Apache 2.0. · GitHub http://github.com/jungroo-ai/redefiner , Apache 2.0, 0.8B, runs on a CPU : python from redefiner import Tagger tagger = Tagger.from pretrained "jungroo-ai/redefiner-0.8b" rulebook = """ RULES Extract every entity of the supplied types. Return exact spans from the text. TYPE PRODUCT DESCRIPTION A product line or model name. TYPE PRICE DESCRIPTION A price or a price limit. PR1 A price limit keeps its limit word in the span: "under $50", "below 30 dollars", "less than $200". """ tagger.extract "your text here", rulebook The README shows that one added line changing “$120” to “under $120” with nothing retrained. You can keep PERSON, ORG and the rest by listing them too. If you have labelled data, use it as a test set: on public benchmarks it scores a few points below large API models, so check it on your own text.