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.
3 Dec 18, 2021
1 Feb 14, 2022
2 Aug 06, 2022
11 Jul 21, 2022
4.8k Jan 03, 2023
1.7k Dec 20, 2022
50 Dec 31, 2022
40 Nov 25, 2022
9 Oct 13, 2022
5.4k Jan 03, 2023
167 Jan 03, 2023
118 Dec 30, 2022
67 Nov 14, 2022
7 Apr 28, 2022
2k Jan 08, 2023
1 May 14, 2022
161 Oct 30, 2022
345 Jan 03, 2023
6.7k Dec 28, 2022
4 Nov 25, 2022