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 2005.08805cs.CL
收藏

长尾多标签分类中的交互匹配

Interaction Matching for Long-Tail Multi-Label Classification

Georgetown University(乔治城大学);Adobe Inc.(奥多比公司)

Sean MacAvaney, Franck Dernoncourt, Walter Chang, Nazli Goharian, Ophir Frieder

摘要:

我们提出了一个优雅的和有效的方法来解决现有的多标签分类模型的局限性,通过将交互匹配,一个概念是有用的ad-hoc搜索结果排名。通过执行软n-gram交互匹配,我们将标签与自然语言描述(这在大多数多标签任务中很常见)进行匹配。我们的方法可以用来增强现有的多标签分类方法,这是偏向于频繁出现的标签。我们评估我们的方法在两个具有挑战性的任务:自动医疗编码的临床笔记和自动标记的实体,从软件教程文本。我们的结果表明,我们的方法可以在宏观性能上产生高达11%的相对改进,其中大部分增益源于训练集中不经常出现的标签(即,标签的长尾)。

英文摘要:

We present an elegant and effective approach for addressing limitations in existing multi-label classification models by incorporating interaction matching, a concept shown to be useful for ad-hoc search result ranking. By performing soft n-gram interaction matching, we match labels with natural language descriptions (which are common to have in most multi-labeling tasks). Our approach can be used to enhance existing multi-label classification approaches, which are biased toward frequently-occurring labels. We evaluate our approach on two challenging tasks: automatic medical coding of clinical notes and automatic labeling of entities from software tutorial text. Our results show that our method can yield up to an 11% relative improvement in macro performance, with most of the gains stemming labels that appear infrequently in the training set (i.e., the long tail of labels).

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。

↑