SpERT torchserve
Spert_torchserve is the Relation Extraction model (SpERT)Span-based Entity and Relation Transformer API deployed with pytorch/serve.
Install Requirements
pip install -r requirements.txt
Get your pretrained model
Train your own model with SpERT or use model trained by CoNLL04 from Huggingface. Only pytorch_model.bin is required to be archived. Download it here and save it into model directory.
You can also save your own model at Huggingface with large file storage.
Archive your model
Before serving model, pack the model and other configs into a .mar file.
torch-model-archiver --model-name spert --version 1.0 --model-file models.py --serialized-file model/pytorch_model.bin --export-path model_store --extra-files entities.py,input_reader.py,loss.py,prediction.py,sampling.py,conll04_types.json --handler spert_handler
This command pack all the needed files into a spert.mar file in model_store fold.
Serve the model
Start the service using the spert.mar with command:
torchserve --start --model-store model_store --models my_tc=spert.mar --ncs
Test
Post the text example "In 1822, the 18th president of the United States, Ulysses S. Grant, was born in Point Pleasant, Ohio" to:
http://127.0.0.1:8080/predictions/my_tc
A prediction would be returned:
{ "tokens": [ "In", "1822", ",", "the", "18th", "president", "of", "the", "United", "States", ",", "Ulysses", "S.", "Grant", ",", "was", "born", "in", "Point", "Pleasant", ",", "Ohio" ], "entities": [ { "type": "Loc", "start": 8, "end": 10 }, { "type": "Peop", "start": 11, "end": 14 }, { "type": "Loc", "start": 18, "end": 22 } ], "relations": [ { "type": "Live_In", "head": 1, "tail": 2 } ] }
References
Markus Eberts, Adrian Ulges. Span-based Joint Entity and Relation Extraction with Transformer Pre-training. 24th European Conference on Artificial Intelligence, 2020.
1.6k Jan 07, 2023
29 Dec 05, 2022
11 Dec 09, 2022
1 Apr 05, 2022
12 Nov 11, 2022
15 Dec 11, 2022
8 Nov 30, 2022
606 Dec 28, 2022
858 Dec 27, 2022
564 Jan 08, 2023
2 May 12, 2022
7 Dec 10, 2022
3.2k Jan 04, 2023
70 Dec 26, 2022
11 Sep 15, 2022
133 Dec 22, 2022
7 Nov 07, 2022
0 Jul 24, 2022
61 Oct 26, 2022
72 Dec 19, 2022