Chris Hokamp's picture
1 17

Chris Hokamp

chokamp
·

AI & ML interests

Machine Translation, Entity Linking, Summarization

Recent Activity

liked a model 8 days ago
tasksource/deberta-small-long-nli
liked a dataset 6 months ago
argilla/magpie-ultra-v0.1
liked a Space 7 months ago
knowledgator/GLiNER_HandyLab
View all activity

Organizations

Aylien Labs's profile picture Open-Source AI Meetup's profile picture

chokamp's activity

reacted to tomaarsen's post with ❤️ 10 months ago
view post
Post
I remember very well that about two years ago, 0-shot named entity recognition (i.e. where you can choose any labels on the fly) was completely infeasible. Fast forward a year, and Universal-NER/UniNER-7B-all surprised me by showing that 0-shot NER is possible! However, I had a bunch of concerns that prevented me from ever adopting it myself. For example, the model was 7B parameters, only worked with 1 custom label at a time, and it had a cc-by-nc-4.0 license.

Since then, a little known research paper introduced GLiNER, which was a modified & finetuned variant of the microsoft/deberta-v3-base line of models. Notably, GLiNER outperforms UniNER-7B, despite being almost 2 orders of magnitude smaller! It also allows for multiple labels at once, supports nested NER, and the models are Apache 2.0.

Very recently, the models were uploaded to Hugging Face, and I was inspired to create a demo for the English model. The demo runs on CPU, and can still very efficiently compute labels with great performance. I'm very impressed at the models.

There are two models right now:
* base (english): urchade/gliner_base
* multi (multilingual): urchade/gliner_multi

And my demo to experiment with the base model can be found here: https://huggingface.co/spaces/tomaarsen/gliner_base
·
liked a Space about 2 years ago
liked a dataset about 2 years ago
liked a Space about 2 years ago