arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.00438cs.CL
收藏

tax2vec:从分类学中构造可解释的特征用于短文本分类

tax2vec: Constructing Interpretable Features from Taxonomies for Short Text Classification

Jožef Stefan Institute(约瑟夫·斯特凡研究所);Jožef Stefan International Postgraduate School(约瑟夫·斯特凡国际研究生院);University of Nova Gorica(新戈里察大学)

Blaž Škrlj, Matej Martinc, Jan Kralj, Nada Lavrač, Senja Pollak

摘要:

在文本分类任务中,背景知识的使用在很大程度上未被利用。本文探讨了词分类作为手段,用于构建新的语义特征,这可能会提高学习分类器的性能和鲁棒性。我们提出了tax2vec,一个并行算法,用于构建基于分类的功能,并展示了其使用六个短文本分类问题:预测性别,性格类型,年龄,新闻主题,药物副作用和药物有效性。构建的语义特征,结合快速线性分类器,测试对强基线,如层次注意神经网络,实现了可比的分类结果短文本文档。该算法的性能也进行了测试,在少样本学习设置,包括语义特征,可以提高在数据稀缺的情况下的性能。tax2vec提取特定于语料库的语义关键字的能力也被证明。最后,我们调查的语义空间的潜在功能,我们观察到的相似性与著名的齐普夫定律。

英文摘要:

The use of background knowledge is largely unexploited in text classification tasks. This paper explores word taxonomies as means for constructing new semantic features, which may improve the performance and robustness of the learned classifiers. We propose tax2vec, a parallel algorithm for constructing taxonomy-based features, and demonstrate its use on six short text classification problems: prediction of gender, personality type, age, news topics, drug side effects and drug effectiveness. The constructed semantic features, in combination with fast linear classifiers, tested against strong baselines such as hierarchical attention neural networks, achieves comparable classification results on short text documents. The algorithm's performance is also tested in a few-shot learning setting, indicating that the inclusion of semantic features can improve the performance in data-scarce situations. The tax2vec capability to extract corpus-specific semantic keywords is also demonstrated. Finally, we investigate the semantic space of potential features, where we observe a similarity with the well known Zipf's law.

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。

↑