Efficient Few-Shot Fine-Tuning for Opinion Summarization. (arXiv:2205.02170v1 [cs.CL])

Web: http://arxiv.org/abs/2205.02170

Abstractive summarization models are typically pre-trained on large amounts
of generic texts, then fine-tuned on tens or hundreds of thousands of annotated
samples. However, in opinion summarization, large annotated datasets of reviews
paired with reference summaries are not available and would be expensive to
create. This calls for fine-tuning methods robust to overfitting on small
datasets. In addition, generically pre-trained models are often not accustomed
to the specifics of customer reviews and, after fine-tuning, yield summaries
with disfluencies and semantic …

arxiv fine-tuning opinion summarization