This paper studies the problem of automated educational test generation. We describe a procedure for generating cloze test items from Russian-language text, which consists of three steps: sentence splitting, sentence filtering, and question generation. The sentence filtering issue is discussed as an application of automatic summarization techniques. We describe a simple experimental system whic...

This article reports on case-study research which explored English as a second language (ESL) learners’ perceptions of the role played by the literary cloze activity in the development of their language and literary awareness. The subjects, four students from a variety of language, culturaland literarybackgrounds, attended a semester-long university ESL subject which adopted a language-based ap...

Cloze test is widely adopted in language exams to evaluate students’ language proficiency. In this paper, we propose the first large-scale human-designed cloze test dataset CLOTH 1, in which the questions were used in middle-school and high-school language exams. With the missing blanks carefully created by teachers and candidate choices purposely designed to be confusing, CLOTH requires a deep...

Reading comprehension ability consists of multiple cognitive processes, and cloze tests have long been claimed to measure this ability as a whole. However, since the introduction of cloze test, different varieties of it have been proposed by the testers. Thus, the present study was an attempt to examine the relatedness of Cloze-Elide test, Multiple-choice (MC) cloze test, and C-test as three di...

Reading in a second language (L2) is complex process that incorporates linguistic knowledge and literacy abilities, as well strategic competence to approach different types of reading tasks depending on goals. However, much the previous research was limited correlational studies focused relative contribution broad categories L2 proficiency first-language (L1) comprehension. investigations into ...

The main intrinsic evaluation for vector space representation has been focused on textual similarity, where the task is to predict how semantically similar two words or sentences are. We propose a novel framework, Story Cloze Evaluator, for evaluating vector representations which goes beyond textual similarity and captures the notion of predicting what should happen next given a context. This e...

Do negative quantifiers like "few" reduce people's ability to rapidly evaluate incoming language with respect to world knowledge? Previous research has addressed this question by examining whether online measures of quantifier comprehension match the "final" interpretation reflected in verification judgments. However, these studies confounded quantifier valence with its impact on the unfolding ...

We describe the automated generation and use of 69,326 comprehension cloze questions and 5,668 vocabulary matching questions in the 2001-2002 version of Project LISTEN’s Reading Tutor used by 364 students in grades 1-9 at seven schools. To validate our methods, we used students’ performance on these multiple-choice questions to predict their scores on the Woodcock Reading Mastery Test. A model ...

Can automatically generated questions scaffold reading comprehension? We automated three kinds of multiple-choice questions in children’s assisted reading: 1. Whquestions: ask a generically worded What/Where/When question. 2. Sentence prediction: ask which of three sentences belongs next. 3. Cloze: ask which of four words best fills in a blank in the next sentence. A within-subject experiment i...

In English reading, Banked Cloze has always been the key and difficult point in examination. Students generally report that is quite to handle. The purpose of this study clarify relationship between reading comprehension metacognitive strategies Cloze, understand how college students use test, so as find effective methods help students’ their CET.