Learning to Reject with a Fixed Predictor: Application to Decontextualization

Christopher Mohri, Daniel Andor, Eunsol Choi, Michael Collins, Anqi Mao, Yutao Zhong

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Rejection, abstention, loss function, consistency, learning theory, decontextualization, natural language processing

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We introduce a new loss function for learning a rejector with a fixed predictor, and focus on the decontextualization task.

Abstract: We study the problem of classification with a reject option for a fixed predictor, crucial to natural language processing. We introduce a new problem formulation for this scenario, and an algorithm minimizing a new surrogate loss function. We provide a complete theoretical analysis of the surrogate loss function with a strong $H$-consistency guarantee. For evaluation, we choose the \textit{decontextualization} task, and provide a manually-labelled dataset of $2\mathord,000$ examples. Our algorithm significantly outperforms the baselines considered, with a $\sim 25$% improvement in coverage when halving the error rate, which is only $\sim 3$% away from the theoretical limit.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: general machine learning (i.e., none of the above)

Submission Number: 9141