arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.04289cs.CLcs.LGcs.NE
收藏

基于神经网络的文本自动评分

Automatic Text Scoring Using Neural Networks

University of Cambridge(剑桥大学)

Dimitrios Alikaniotis, Helen Yannakoudakis, Marek Rei

摘要:

自动文本评分(ATS)为人工标记提供了一种具有成本效益且一致的替代方案。然而,为了实现良好的性能,系统的预测功能需要由人类专家手动设计。我们引入了一个模型,通过学习特定单词对文本分数的贡献程度来形成单词表示。使用长短期记忆网络来表示文本的含义,我们证明了一个完全自动化的框架能够在类似的方法上取得优异的结果。为了使我们的结果更具可解释性,并受到可视化神经网络的最新进展的启发,我们引入了一种新的方法来识别模型发现更具歧视性的文本区域。

英文摘要:

Automated Text Scoring (ATS) provides a cost-effective and consistent alternative to human marking. However, in order to achieve good performance, the predictive features of the system need to be manually engineered by human experts. We introduce a model that forms word representations by learning the extent to which specific words contribute to the text's score. Using Long-Short Term Memory networks to represent the meaning of texts, we demonstrate that a fully automated framework is able to achieve excellent results over similar approaches. In an attempt to make our results more interpretable, and inspired by recent advances in visualizing neural networks, we introduce a novel method for identifying the regions of the text that the model has found more discriminative.

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。

↑