EQG-RACE: Examination-Type Question Generation

نویسندگان

چکیده

Question Generation (QG) is an essential component of the automatic intelligent tutoring systems, which aims to generate high-quality questions for facilitating reading practice and assessments. However, existing QG technologies encounter several key issues concerning biased unnatural language sources datasets are mainly obtained from Web (e.g. SQuAD). In this paper, we propose innovative Examination-type approach (EQG-RACE) exam-like based on a dataset extracted RACE. Two main strategies employed in EQG-RACE dealing with discrete answer information reasoning among long contexts. A Rough Answer Key Sentence Tagging scheme utilized enhance representations input. An Answer-guided Graph Convolutional Network (AG-GCN) designed capture structure revealing inter-sentences intra-sentence relations. Experimental results show state-of-the-art performance EQG-RACE, apparently superior baselines. addition, our work has established new prototype reshaped method, provides important benchmark related research future work. We will make data code publicly available further research.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Question of Race

IN the "Lancet" of 17th October, 1942, it was shown by Ridehalgh that Irish nurses seemed to be more susceptible to tuberculosis than those of Great Britain; this was followed by a leading article on 31st October, 1942, on Tuberculosis in Eire. Again attention was called to the apparent susceptibility of the inhabitants of Ireland to tuberculosis. This is a subject which has interested me since...

متن کامل

Question Generation for Question Answering

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...

متن کامل

Good Question! Statistical Ranking for Question Generation

We address the challenge of automatically generating questions from reading materials for educational practice and assessment. Our approach is to overgenerate questions, then rank them. We use manually written rules to perform a sequence of general purpose syntactic transformations (e.g., subject-auxiliary inversion) to turn declarative sentences into questions. These questions are then ranked ...

متن کامل

Question Paraphrase Generation for Question Answering System

The queries to a practical Question Answering (QA) system range from keywords, phrases, badly written questions, and occasionally grammatically perfect questions. Among different kinds of question analysis approaches, the pattern matching works well in analyzing such queries. It is costly to build this pattern matching module because tremendous manual labor is needed to expand its coverage to s...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence

سال: 2021

ISSN: ['2159-5399', '2374-3468']

DOI: https://doi.org/10.1609/aaai.v35i14.17553