Fine-tuned Language Models for Text Classification

@article{Howard2018FinetunedLM,
  title={Fine-tuned Language Models for Text Classification},
  author={Jeremy Howard and Sebastian Ruder},
  journal={CoRR},
  year={2018},
  volume={abs/1801.06146}
}
Transfer learning has revolutionized computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Fine-tuned Language Models (FitLaM), an effective transfer learning method that can be applied to any task in NLP, and introduce techniques that are key for fine-tuning a state-of-the-art language model. Our method significantly outperforms the state-of-the-art on five text classification tasks, reducing the error by 1824% on the… CONTINUE READING
Highly Cited
This paper has 38 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 393 times. VIEW TWEETS

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 52 references

Fully Convolutional Networks for Semantic Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2015
View 7 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…