Bart Finetuned Keyphrase Extraction

🚀 BART fine-tuned for keyphrase generation

This model is a fine - tuned version of bart - base (Lewis et al., 2019) for the keyphrase generation task (Glazkova & Morozov, 2023). It is trained on fragments of the following corpora:

• Krapivin (Krapivin et al., 2009)
• Inspec (Hulth, 2003)
• KPTimes (Gallina, 2019)
• DUC - 2001 (Wan, 2008)
• PubMed (Schutz, 2008)
• NamedKeys (Gero & Ho, 2019)

🚀 Quick Start

📋 Datasets

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("aglazkova/bart_finetuned_keyphrase_extraction")
model = AutoModelForSeq2SeqLM.from_pretrained("aglazkova/bart_finetuned_keyphrase_extraction")

text = "In this paper, we investigate cross-domain limitations of keyphrase generation using the models for abstractive text summarization.\
        We present an evaluation of BART fine-tuned for keyphrase generation across three types of texts, \
        namely scientific texts from computer science and biomedical domains and news texts. \
        We explore the role of transfer learning between different domains to improve the model performance on small text corpora."

tokenized_text = tokenizer.prepare_seq2seq_batch([text], return_tensors='pt')
translation = model.generate(**tokenized_text)
translated_text = tokenizer.batch_decode(translation, skip_special_tokens=True)[0]
print(translated_text)

📚 Documentation

Training Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 4e - 5
• train_batch_size: 8
• optimizer: AdamW with betas=(0.9, 0.999) and epsilon = 1e - 08
• num_epochs: 6

📄 License

BibTeX:

@InProceedings{10.1007/978-3-031-67826-4_19,
author="Glazkova, Anna
and Morozov, Dmitry",
title="Cross-Domain Robustness of Transformer-Based Keyphrase Generation",
booktitle="Data Analytics and Management in Data Intensive Domains",
year="2024",
publisher="Springer Nature Switzerland",
address="Cham",
pages="249--265"
}