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 1806.06219cs.CL
收藏

GILE:一种用于文本分类的广义输入标签嵌入算法

GILE: A Generalized Input-Label Embedding for Text Classification

Idiap Research Institute(IDIAP研究所)

Nikolaos Pappas, James Henderson

摘要:

神经文本分类模型通常将输出标签视为缺乏描述和语义的分类变量。这迫使它们的参数化依赖于标签集的大小,因此,它们无法扩展到大型标签集并推广到不可见的标签集。现有的联合输入标签文本模型通过利用标签描述来克服这些问题,但它们无法捕获复杂的标签关系,具有严格的参数化,并且它们在看不见的标签上的增益通常是以训练期间看到的标签的弱性能为代价的。在本文中,我们提出了一个新的输入标签模型,它概括了以前的这种模型,解决了它们的局限性,并且不会影响看到的标签的性能。该模型由一个容量可控的联合非线性输入-标签嵌入和一个联合空间相关的分类单元组成,该分类单元采用交叉熵损失进行训练以优化分类性能。我们评估模型的全资源和低或零资源的多语言新闻和生物医学文本分类与一个大的标签集。我们的模型优于单语和多语言模型,不利用标签语义和以前的联合输入标签空间模型在这两种情况下。

英文摘要:

Neural text classification models typically treat output labels as categorical variables which lack description and semantics. This forces their parametrization to be dependent on the label set size, and, hence, they are unable to scale to large label sets and generalize to unseen ones. Existing joint input-label text models overcome these issues by exploiting label descriptions, but they are unable to capture complex label relationships, have rigid parametrization, and their gains on unseen labels happen often at the expense of weak performance on the labels seen during training. In this paper, we propose a new input-label model which generalizes over previous such models, addresses their limitations and does not compromise performance on seen labels. The model consists of a joint non-linear input-label embedding with controllable capacity and a joint-space-dependent classification unit which is trained with cross-entropy loss to optimize classification performance. We evaluate models on full-resource and low- or zero-resource text classification of multilingual news and biomedical text with a large label set. Our model outperforms monolingual and multilingual models which do not leverage label semantics and previous joint input-label space models in both scenarios.

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。

↑