Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference Feedback

Duy-Hung Nguyen, Nguyen-Viet-Dung Nghiem, Bao-Sinh Nguyen, Dung Tien Le, Shahab Sabahi, Minh-Tien Nguyen, Hung Le

Abstract

For summarization, human preference is critical to tame outputs of the summarizer in favor of human interests, as ground-truth summaries are scarce and ambiguous. Practical settings require dynamic exchanges between human and AI agent wherein feedback is provided in an online manner, a few at a time. In this paper, we introduce a new framework to train summarization models with preference feedback interactively. By properly leveraging offline data and a novel reward model, we improve the performance regarding ROUGE scores and sample-efficiency. Our experiments on three various datasets confirm the benefit of the proposed framework in active, few-shot and online settings of preference learning.
BibTeX
@inproceedings{nguyen2022make,
  author = {Duy-Hung Nguyen and Nguyen-Viet-Dung Nghiem and Bao-Sinh Nguyen and Dung Tien Le and Shahab Sabahi and Minh-Tien Nguyen and Hung Le},
  title = {{Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference Feedback}},
  booktitle = {Conference of the North American Chapter of the Association for Computational Linguistics},
  year = {2022},
  url = {https://openreview.net/forum?id=skzUDpmI0aj},
}

Loading related content...

Figure