This paper presents how to generate questions from given passages using neural networks, where large scale QA pairs are automatically crawled and processed from Community-QA website, and used as training data. The contribution of the paper is 2-fold: First, two types of question generation approaches are proposed, one is a retrieval-based method using convolution neural network (CNN), the other...

In order to represent, compute and reason with advanced data types one must go beyond the traditional treatment of data types as being inductive types and, instead, consider them as inductive families. Strictly positive types (SPTs) form a grammar for defining inductive types and, consequently, a fundamental question in the theory of inductive families is what constitutes a corresponding gramma...

the present study is an attempt to contribute to the l2 acquisition research through finding an appropriate answer to the question usually asked by both language teachers and learners, namely how to learn vocabulary and how to retain meanings in memory over time. we have chosen to discover the effects of two major types of productive exercises, writing and oral production exercises, on the reme...

the present study aimed at investigating the possible impact ofzone of proximal development (zpd) on the learners’ performance. forty-sixiranian university students participated in this study by taking two types of readingcomprehension tests (i.e., the main idea and wh-question type). the researchersused the winstep program to analyze the data and estimate the learners’ raschmeasure in pre, pos...

The way that complainants of child sexual assault are questioned about their experiences can profoundly influence the accuracy, credibility, and consistency evidence. This is case for all people, but especially children whose language, social, cognitive capacity still developing. In this study, we examined questions used by a representative sample Australian prosecutors, defense lawyers, judges...

Questions have been analyzed in Estonian information dialogues with the purpose of finding out the linguistic features that can be used in automatic recognition of various types of questions. Information questions (i.e. the questions that are used for requesting information) and questions that initiate solving communication problems are considered. The study shows which types of questions (wh-q...

This paper describes a Korean Question Answering (KorQuA) system. For flexible text retrieval, we represent terms in a question as five data types, and retrieve passages by matching terms according to these data types. In answer extraction, we filter non-fact answers with negative or uncertain contexts, and interpret a relative expression as an absolute date answer for date type question. Throu...