Predicting the Difficulty of Language Proficiency Tests
Predicting the Difficulty of Language Proficiency Tests
复制标题
预测语言能力测试的难度
DOI：
10.1162/tacl_a_00200
复制
发表时间：
2014
影响因子：
10.9
通讯作者：
Iryna Gurevych
中科院分区：
文献类型：
--
作者：
Lisa Beinborn;Torsten Zesch;Iryna Gurevych
语言水平测试是用来评估和比较语言学习者的进步。我们提出了一种自动预测C-测试难度的方法，其表现与人类专家不相上下。在对新收集的数据进行详细分析的基础上，我们建立了一个C测试难度模型，该模型引入了四个维度：解决难度、候选歧义、间隙依赖和段落难度。我们发现，从所有四个维度的线索有助于C-测试难度。
Language proficiency tests are used to evaluate and compare the progress of language learners. We present an approach for automatic difficulty prediction of C-tests that performs on par with human experts. On the basis of detailed analysis of newly collected data, we develop a model for C-test difficulty introducing four dimensions: solution difficulty, candidate ambiguity, inter-gap dependency, and paragraph difficulty. We show that cues from all four dimensions contribute to C-test difficulty.