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.
翻译:对于极端多标签分类(XMC),现有的基于分类的模型在尾标签方面表现不佳,常常忽视标签之间的语义关系,例如将“维基百科”和“维基”作为独立和独立的标签。在本文中,我们将XMC作为一个代代任务(XLGen),我们从经过预先培训的文本到文本模型中获益。然而,从极大型标签空间生成标签具有挑战性,没有任何限制或指导。因此,我们提议用标签群集信息指导标签的生成,以便按等级生成较低等级的标签。我们还发现,基于频率的标签订购和使用解码共用的方法是XLGen. XLGen的改进的关键因素,而集束指导大大超越了尾标签的分类和生成基线,并普遍改进了四种流行的XMC基准的总体性。在人类评估中,我们也发现XLGen生成了看不见但可信的标签。我们的代码现在可在https://github.com/alexa/xlgen-ecl-2023查阅。