arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.00129cs.CLcs.LG
收藏

基于结构标记的文本分类算法在学术文献质量预测中的应用

Structure-Tags Improve Text Classification for Scholarly Document Quality Prediction

Center for Information Technology, University of Groningen(格罗宁根大学信息技术中心);Kapteyn Astronomical Institute, University of Groningen(格罗宁根大学卡普泰恩天文研究所)

Gideon Maillette de Buy Wenniger, Thomas van Dongen, Eleri Aedmaa, Herbert Teun Kruitbosch, Edwin A. Valentijn, Lambert Schomaker

摘要:

在长文本(特别是学术文档)上训练递归神经网络会给学习带来问题。虽然层次注意力网络(HAN)在解决这些问题方面是有效的,但它们仍然丢失了关于文本结构的重要信息。为了解决这些问题,我们建议使用HAN与结构标签相结合,标记文档中句子的作用。为句子添加标签,将它们标记为与标题,摘要或主体文本相对应,从而改进了学术文档质量预测的最新技术。所提出的系统被应用到接受/拒绝的PeerRead数据集上的预测任务,并与最近的基于BiLSTM的模型和联合文本+视觉模型以及普通HAN进行比较。与普通HAN相比,在所有三个域上的准确性都有所提高。在计算和语言领域,我们的新模型总体上效果最好,比最佳文献结果提高了4.7%的准确性。我们还在引入用于预测我们从Allen AI S2 ORC数据集编译的88 k科学出版物的引用数量的标签时获得了改进。对于我们的HAN系统与结构标签,我们达到了28.5%的解释方差,比我们的基于BiLSTM的模型的重新实现提高了1.8%,比普通HAN提高了1.0%。

英文摘要:

Training recurrent neural networks on long texts, in particular scholarly documents, causes problems for learning. While hierarchical attention networks (HANs) are effective in solving these problems, they still lose important information about the structure of the text. To tackle these problems, we propose the use of HANs combined with structure-tags which mark the role of sentences in the document. Adding tags to sentences, marking them as corresponding to title, abstract or main body text, yields improvements over the state-of-the-art for scholarly document quality prediction. The proposed system is applied to the task of accept/reject prediction on the PeerRead dataset and compared against a recent BiLSTM-based model and joint textual+visual model as well as against plain HANs. Compared to plain HANs, accuracy increases on all three domains. On the computation and language domain our new model works best overall, and increases accuracy 4.7% over the best literature result. We also obtain improvements when introducing the tags for prediction of the number of citations for 88k scientific publications that we compiled from the Allen AI S2ORC dataset. For our HAN-system with structure-tags we reach 28.5% explained variance, an improvement of 1.8% over our reimplementation of the BiLSTM-based model as well as 1.0% improvement over plain HANs.

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。

↑