Text Classification
Transformers
PyTorch
English
roberta
climate
Inference Endpoints
kdutia's picture
add padding and truncation arguments to `pipe` example
7aa98b4 verified
|
raw
history blame
2.7 kB
metadata
license: apache-2.0
datasets:
  - ClimatePolicyRadar/national-climate-targets
language:
  - en
pipeline_tag: text-classification
tags:
  - climate
widget:
  - text: >-
      The Net Zero Strategy, published in October 2021, was the first document
      of its kind for a major economy. It set out the government’s vision for a
      market-led, technology-driven transition to decarbonise the UK economy and
      reach net zero by 2050.
inference:
  parameters:
    function_to_apply: sigmoid

National Climate Targets Classifier - Climate Policy Radar

A multi-label text-classifier trained on the National Climate Targets dataset by Climate Policy Radar.

Using the climatebert/distilroberta-base-climate-f model as a starting point, this classifier is trained on the ClimatePolicyRadar/national-climate-targets dataset to predict Net Zero ("NZT") , "Reduction" and "Other" targets in a multi-label setting. The training data is an expert annotated subset of national laws, policies and UNFCCC submissions.

For more information on the annotation methodology and classifier training see our paper TBA.

Getting started

from transformers import AutoModelForSequenceClassification, AutoTokenizer


model_name = "ClimatePolicyRadar/national-climate-targets"
example = "The Net Zero Strategy, published in October 2021, was the first "\
    "document of its kind for a major economy. It set out the government’s "\
    "vision for a market-led, technology-driven transition to decarbonise "\
    "the UK economy and reach net zero by 2050."


model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# using sigmoid because the model is multi-label
pipe = pipeline("text-classification", model=model, tokenizer=tokenizer, function_to_apply="sigmoid")


pipe(example, padding=True, truncation=True)

>>> [{'label': 'NZT', 'score': 0.9142044186592102}]

Licence

Our classifier is licensed as Apache 2.0.

Please read our Terms of Use, including any specific terms relevant to commercial use. Contact [email protected] with any questions.

Links

  • Repository: [coming soon]
  • Paper: [coming soon]

Citation

[coming soon]

Authors & Contact

Climate Policy Radar team: Matyas Juhasz, Tina Marchand, Roshan Melwani, Kalyan Dutia, Sarah Goodenough, Harrison Pim, and Henry Franks.

[email protected]

https://climatepolicyradar.org