Model Card for Model ID
Model Details
Model Description
This model was fine-tuned on addresses from Canada open data portal to parse Canadian addresses into ["B-STREET_NO", "I-STREET_NO", "B-STREET_NAME", "I-STREET_NAME", "B-STREET_TYPE", "I-STREET_TYPE", "B-STREET_DIR","I-STREET_DIR", "B-CITY", "I-CITY"] The results with the same tag need to be concatenated to provide meaningful output; please see section "How to Get Started with the Model" for inference example.
- Developed by: [Juntao Zhang]
- Funded by [optional]: [More Information Needed]
- Shared by [optional]: [More Information Needed]
- Model type: [BERT-based token classification model]
- Language(s) (NLP): [More Information Needed]
- License: [More Information Needed]
- Finetuned from model [optional]: [bert-base-uncased]
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
Direct Use
[This model can be used for token classification tasks, such as named entity recognition (NER) or address token classification. ]
Downstream Use [optional]
[address matching, address auto-correction etc.]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
How to Get Started with the Model
Use the code below to get started with the model.
[
import torch
from transformers import pipeline
import os
import json
class GeoLLMBertInference:
def __init__(self, config_path='config.json'):
with open(config_path, 'r') as config_file:
config = json.load(config_file)
self.project_path = config['project_path']
self.tokenizer_path = os.path.join(self.project_path, config['tokenizer_path'])
self.model_path = os.path.join(self.project_path, config['model_path'])
# Check if a GPU is available and set the device accordingly
self.device = 0 if torch.cuda.is_available() else -1
self.ner_pipeline = pipeline("ner", model=self.model_path, tokenizer=self.tokenizer_path, device=self.device)
self.result = None
self.concatenate_result = None
def get_ner_result(self, address):
self.result = self.ner_pipeline(address.upper())
return self.result
def concatenate_entities(self):
if self.result is None:
raise ValueError("NER result is not available. Please run get_ner_result first.")
concatenated_result = {}
for entity in self.result:
tag = entity['entity']
word = entity['word'].replace('##', '').replace(',', '')
if tag not in concatenated_result:
concatenated_result[tag] = word.upper()
else:
concatenated_result[tag] += '' + word.upper()
self.concatenate_result = concatenated_result
return self.concatenate_result
def get_json_result(self):
if self.concatenate_result is None:
raise ValueError("Concatenated result is not available. Please run concatenate_entities first.")
return json.dumps(self.concatenate_result, indent=4)
# Example Usage
if __name__ == "__main__":
geo_llm = GeoLLMBertInference('code/geo_llm/config.json')
address = "16 ChSeAStREtST.CATHARINE"
result = geo_llm.get_ner_result(address)
print(result)
concatenate_result = geo_llm.concatenate_entities()
print(concatenate_result)
# Get the concatenated result in JSON format
json_result = geo_llm.get_json_result()
data = json.loads(json_result)
# Print the JSON string
print(json_result)
]
Training Details
Training Data
[More Information Needed]
Training Procedure
Preprocessing [optional]
[More Information Needed]
Training Hyperparameters
- Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
[More Information Needed]
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: [More Information Needed]
- Hours used: [More Information Needed]
- Cloud Provider: [More Information Needed]
- Compute Region: [More Information Needed]
- Carbon Emitted: [More Information Needed]
Technical Specifications [optional]
Model Architecture and Objective
[More Information Needed]
Compute Infrastructure
[More Information Needed]
Hardware
[More Information Needed]
Software
[More Information Needed]
Citation [optional]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Model Card Authors [optional]
[More Information Needed]
Model Card Contact
[More Information Needed]
- Downloads last month
- 35
Model tree for Hythcliff/canadian-address-parser-on
Base model
google-bert/bert-base-uncased