multilingual-IPTC-news-topic-classifier

from transformers import pipeline

# Load a multi-class classification pipeline - if the model runs on CPU, comment out "device"
classifier = pipeline("text-classification", model="classla/multilingual-IPTC-news-topic-classifier", device=0, max_length=512, truncation=True)

# Example texts to classify
texts = [
    """Slovenian handball team makes it to Paris Olympics semifinal Lille, 8 August - Slovenia defeated Norway 33:28 in the Olympic men's handball tournament in Lille late on Wednesday to advance to the semifinal where they will face Denmark on Friday evening. This is the best result the team has so far achieved at the Olympic Games and one of the best performances in the history of Slovenia's team sports squads.""",
	"""Moment dog sparks house fire after chewing power bank An indoor monitoring camera shows the moment a dog unintentionally caused a house fire after chewing on a portable lithium-ion battery power bank. In the video released by Tulsa Fire Department in Oklahoma, two dogs and a cat can be seen in the living room before a spark started the fire that spread within minutes. Tulsa Fire Department public information officer Andy Little said the pets escaped through a dog door, and according to local media the family was also evacuated safely. "Had there not been a dog door, they very well could have passed away," he told CBS affiliate KOTV."""]

# Classify the texts
results = classifier(texts)

# Output the results
for result in results:
    print(result)

## Output
## {'label': 'sport', 'score': 0.9985264539718628}
## {'label': 'disaster, accident and emergency incident', 'score': 0.9957459568977356}

labels_list=['education', 'human interest', 'society', 'sport', 'crime, law and justice',
'disaster, accident and emergency incident', 'arts, culture, entertainment and media', 'politics',
'economy, business and finance', 'lifestyle and leisure', 'science and technology',
'health', 'labour', 'religion', 'weather', 'environment', 'conflict, war and peace'],

labels_map={0: 'education', 1: 'human interest', 2: 'society', 3: 'sport', 4: 'crime, law and justice',
5: 'disaster, accident and emergency incident', 6: 'arts, culture, entertainment and media',
7: 'politics', 8: 'economy, business and finance', 9: 'lifestyle and leisure', 10: 'science and technology',
11: 'health', 12: 'labour', 13: 'religion', 14: 'weather', 15: 'environment', 16: 'conflict, war and peace'}

model_args = ClassificationArgs()

model_args ={
             "num_train_epochs": 5,
             "learning_rate": 8e-06,
             "train_batch_size": 32,
             "max_seq_length": 512,
             }   
      

@ARTICLE{10900365,
  author={Kuzman, Taja and Ljubešić, Nikola},
  journal={IEEE Access}, 
  title={LLM Teacher-Student Framework for Text Classification With No Manually Annotated Data: A Case Study in IPTC News Topic Classification}, 
  year={2025},
  volume={},
  number={},
  pages={1-1},
  keywords={Data models;Annotations;Media;Manuals;Multilingual;Computational modeling;Training;Training data;Transformers;Text categorization;Multilingual text classification;IPTC;large language models;LLMs;news topic;topic classification;training data preparation;data annotation},
  doi={10.1109/ACCESS.2025.3544814}}

@misc{iptc_topic_model,
	author       = { Kuzman, Taja and Ljube{\v s}i{\'c}, Nikola },
	title        = {{ Multilingual IPTC News Topic Classifier}},
	year         = 2025,
	url          = { https://huggingface.co/classla/multilingual-IPTC-news-topic-classifier },
	doi          = { 10.57967/hf/4709 },
	publisher    = { Hugging Face }
}