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 1609.04909cs.CL
收藏

基于迭代迁移学习的简答题自动评分方法

An Iterative Transfer Learning Based Ensemble Technique for Automatic Short Answer Grading

Xerox Research Centre India(施乐印度研究中心);Indian Institute of Science(印度科学院)

Shourya Roy, Himanshu S. Bhatt, Y. Narahari

摘要:

自动简短回答评分(ASAG)技术被设计为自动评估对自然语言中的问题的简短回答,其具有几个单词到几个句子的长度。监督ASAG技术已被证明是有效的,但受到一些关键的实际限制。他们在很大程度上依赖于教师提供的模型答案,并且需要以每个评估任务的分级学生答案的形式标记的训练数据。为了克服这些,在本文中,我们介绍了一个ASAG技术与两个新的功能。我们提出了一种迭代技术的合奏(a)学生答案的文本分类器和(b)分类器使用数值特征来自各种相似性措施的模型答案。其次,我们采用典型相关分析的基础上的一个共同的特征表示迁移学习,建立分类器集成的问题没有标记的数据。所提出的技术漂亮地击败了来自SemEval 2013的学生响应分析任务的SCIENTSBANK数据集上的所有获奖监督条目。此外,我们通过对来自不同主题和标准的多个ASAG数据集进行评估,展示了所提出的技术的通用性和优点。

英文摘要:

Automatic short answer grading (ASAG) techniques are designed to automatically assess short answers to questions in natural language, having a length of a few words to a few sentences. Supervised ASAG techniques have been demonstrated to be effective but suffer from a couple of key practical limitations. They are greatly reliant on instructor provided model answers and need labeled training data in the form of graded student answers for every assessment task. To overcome these, in this paper, we introduce an ASAG technique with two novel features. We propose an iterative technique on an ensemble of (a) a text classifier of student answers and (b) a classifier using numeric features derived from various similarity measures with respect to model answers. Second, we employ canonical correlation analysis based transfer learning on a common feature representation to build the classifier ensemble for questions having no labelled data. The proposed technique handsomely beats all winning supervised entries on the SCIENTSBANK dataset from the Student Response Analysis task of SemEval 2013. Additionally, we demonstrate generalizability and benefits of the proposed technique through evaluation on multiple ASAG datasets from different subject topics and standards.

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。

↑