arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.09044cs.LG
收藏

学习用固定的预测器进行预测:应用于去语境化

Learning to Reject with a Fixed Predictor: Application to Decontextualization

Christopher Mohri, Daniel Andor, Eunsol Choi, Michael Collins

摘要:

本文研究了适用于自然语言处理中的固定预测器带有拒绝选项的分类问题。我们引入了一个新的问题制定这种情况下,和算法最小化一个新的代理损失函数。我们提供了一个完整的理论分析的替代损失函数与强大的$H$一致性保证。为了进行评估,我们选择了去语境化任务,并提供了一个手动标记的$2\mathord,000$示例数据集。我们的算法显着优于基线考虑,与$\sim\!\!25\%$改善覆盖率减半时的出错率,这是只有$\sim\!\! 3 \%$远离理论极限。

英文摘要:

We study the problem of classification with a reject option for a fixed predictor, applicable in 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 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑