metadata

datasets:
  - midas/krapivin
  - midas/inspec
  - midas/kptimes
  - midas/duc2001
language:
  - en
widget:
  - text: >-
      Relevance has traditionally been linked with feature subset selection, but
      formalization of this link has not been attempted. In this paper, we
      propose two axioms for feature subset selection sufficiency axiom and
      necessity axiombased on which this link is formalized: The expected
      feature subset is the one which maximizes relevance. Finding the expected
      feature subset turns out to be NP-hard. We then devise a heuristic
      algorithm to find the expected subset which has a polynomial time
      complexity. The experimental results show that the algorithm finds good
      enough subset of features which, when presented to C4.5, results in better
      prediction accuracy.
  - 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.

BART fine-tuned for keyphrase generation

This is the bart-base (Lewis et al.. 2019) model finetuned for the keyphrase generation task (Glazkova & Morozov, 2023) on the 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).

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

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

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

BibTeX:

@article{glazkova2023cross,
  title={Cross-Domain Robustness of Transformer-based Keyphrase Generation},
  author={Glazkova, Anna and Morozov, Dmitry},
  journal={arXiv preprint arXiv:2312.10700},
  year={2023}
}