arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.02363cs.LGcs.CL
收藏

混合注意下的切片感知表示学习

Learning Slice-Aware Representations with Mixture of Attentions

Amazon Alexa AI(亚马逊Alexa人工智能部门)

Cheng Wang, Sungjin Lee, Sunghyun Park, Han Li, Young-Bum Kim, Ruhi Sarikaya

摘要:

现实世界的机器学习系统在粗粒度指标(如整体准确性和F-1分数)方面取得了显着的性能。然而,模型改进和开发通常需要对单个数据子集或切片进行细粒度建模,例如,模型结果不令人满意的数据切片。在实践中,它为开发这样的模型提供了切实的价值,这些模型可以在保留原始整体性能的同时,额外关注关键或感兴趣的切片。本文扩展了最近的基于切片的学习(SBL)~ \cite{chen2019slice}与混合注意(MoA)来学习切片感知的双重注意表示。我们的经验表明,MoA方法优于基线方法以及原始SBL方法对两个自然语言理解(NLU)任务的监控切片。

英文摘要:

Real-world machine learning systems are achieving remarkable performance in terms of coarse-grained metrics like overall accuracy and F-1 score. However, model improvement and development often require fine-grained modeling on individual data subsets or slices, for instance, the data slices where the models have unsatisfactory results. In practice, it gives tangible values for developing such models that can pay extra attention to critical or interested slices while retaining the original overall performance. This work extends the recent slice-based learning (SBL)~\cite{chen2019slice} with a mixture of attentions (MoA) to learn slice-aware dual attentive representations. We empirically show that the MoA approach outperforms the baseline method as well as the original SBL approach on monitored slices with two natural language understanding (NLU) tasks.

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。

↑