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.
105 Jan 08, 2022
20 Dec 29, 2022
64 May 08, 2022
2 Sep 27, 2022
8 May 19, 2022
180 Dec 09, 2022
0 Aug 06, 2021
11 Jul 21, 2022
134 Dec 16, 2022
762 Dec 29, 2022
32 Oct 14, 2022
113 Dec 28, 2022
103 Dec 26, 2022
40 Sep 28, 2022
1 Apr 05, 2022
132 Nov 25, 2022
26 Sep 20, 2022
35 Sep 20, 2022
169 Dec 21, 2022
2 Dec 31, 2021