arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.09150cs.CLcs.LG
收藏

极端多标签分类中的分类器引导标签生成

Cluster-Guided Label Generation in Extreme Multi-Label Classification

Amazon Alexa AI(亚马逊Alexa人工智能);University of Minnesota(明尼苏达大学)

Taehee Jung, Joo-Kyung Kim, Sungjin Lee, Dongyeop Kang

摘要:

对于极端多标签分类(XMC),现有的基于分类的模型对尾部标签的分类效果不佳,并且常常忽略标签之间的语义关系,例如将“Wikipedia”和“Wiki”视为独立的标签。在本文中,我们将XMC转换为生成任务(XLGen),在这里我们受益于预训练的文本到文本模型。然而,在没有任何约束或指导的情况下,从极大的标签空间生成标签是具有挑战性的。因此,我们建议使用标签聚类信息来指导标签生成,以分层方式生成较低级别的标签。我们还发现,基于频率的标签排序和使用解码集成方法是XLGen改进的关键因素。具有集群指导的XLGen在尾部标签上的性能显著优于分类和生成基线,并且在四个流行的XMC基准测试中也普遍提高了整体性能。在人体评价中,我们还发现XLGen生成看不见但似乎合理的标签。我们的代码现在可以在https://github.com/alexa/xlgen-eacl-2023上找到。

英文摘要:

For extreme multi-label classification (XMC), existing classification-based models poorly perform for tail labels and often ignore the semantic relations among labels, like treating "Wikipedia" and "Wiki" as independent and separate labels. In this paper, we cast XMC as a generation task (XLGen), where we benefit from pre-trained text-to-text models. However, generating labels from the extremely large label space is challenging without any constraints or guidance. We, therefore, propose to guide label generation using label cluster information to hierarchically generate lower-level labels. We also find that frequency-based label ordering and using decoding ensemble methods are critical factors for the improvements in XLGen. XLGen with cluster guidance significantly outperforms the classification and generation baselines on tail labels, and also generally improves the overall performance in four popular XMC benchmarks. In human evaluation, we also find XLGen generates unseen but plausible labels. Our code is now available at https://github.com/alexa/xlgen-eacl-2023.

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。

↑