scholarly journals Difficulty Controllable Generation of Reading Comprehension Questions

2019 ◽  
Author(s):  
Yifan Gao ◽  
Lidong Bing ◽  
Wang Chen ◽  
Michael Lyu ◽  
Irwin King
Keyword(s):  
Reading Comprehension ◽  
Question Generation ◽  
Text Fragment ◽  
End To End

We investigate the difficulty levels of questions in reading comprehension datasets such as SQuAD, and propose a new question generation setting, named Difficulty-controllable Question Generation (DQG). Taking as input a sentence in the reading comprehension paragraph and some of its text fragments (i.e., answers) that we want to ask questions about, a DQG method needs to generate questions each of which has a given text fragment as its answer, and meanwhile the generation is under the control of specified difficulty labels---the output questions should satisfy the specified difficulty as much as possible. To solve this task, we propose an end-to-end framework to generate questions of designated difficulty levels by exploring a few important intuitions. For evaluation, we prepared the first dataset of reading comprehension questions with difficulty labels. The results show that the question generated by our framework not only have better quality under the metrics like BLEU, but also comply with the specified difficulty labels.

scholarly journals Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

2019 ◽  
Author(s):  
Minghao Hu ◽  
Yuxing Peng ◽  
Zhen Huang ◽  
Dongsheng Li
Keyword(s):  
Reading Comprehension ◽  
End To End

Automatic generation of short answer questions for reading comprehension assessment

2016 ◽  
Vol 22 (3) ◽  
pp. 457-489 ◽  
Author(s):  
YAN HUANG ◽  
LIANZHEN HE
Keyword(s):  
Reading Comprehension ◽  
Cognitive Complexity ◽  
Automatic Generation ◽  
Functional Grammar ◽  
Question Generation ◽  
High Performing ◽  
Lexical Functional Grammar ◽  
Short Answer ◽  
Syntactic Information ◽  
Short Answer Questions

AbstractWriting items for reading comprehension assessment is time-consuming. Automating part of the process can help test-designers to develop assessments more efficiently and consistently. This paper presents an approach to automatically generating short answer questions for reading comprehension assessment. Our major contribution is to introduce Lexical Functional Grammar (LFG) as the linguistic framework for question generation, which enables systematic utilization of semantic and syntactic information. The approach can efficiently generate questions of better quality than previous high-performing question generation systems, and uses paraphrasing and sentence selection to improve the cognitive complexity and effectiveness of questions.

scholarly journals Improving students’ reading comprehension achievement through question generation strategy

2020 ◽  
Vol 5 (2) ◽  
pp. 121-127
Author(s):  
Meti Yulistia ◽  
Kiki Rizki Amelia
Keyword(s):  
Reading Comprehension ◽  
The Other ◽  
Control Group ◽  
Question Generation ◽  
Significant Difference ◽  
Reading Text ◽  
Group Reading ◽  
Comprehension Tests ◽  
Experimental Group ◽  
Better Than

This study was aimed to find out whether or not there was a significant difference in reading comprehension achievement between students who were taught by using the Question Generation strategy and that of those who were not. In conducting the study, question generation strategy was used in the experimental group, but the control group did not get any treatment. Sixty students were assigned in two groups, with 30 students in the experimental group and the other 30 students in the control group. Reading comprehension tests was used in collecting the data. Data were analyzed using a t-test. The findings of the study showed that the question generation strategy could improve students’ reading achievement better than and those who were not. Therefore, the question generation strategy was helpful to aid students to understand the reading text

scholarly journals Capturing Greater Context for Question Generation

2020 ◽  
Vol 34 (05) ◽  
pp. 9065-9072
Author(s):  
Luu Anh Tuan ◽  
Darsh Shah ◽  
Regina Barzilay
Keyword(s):  
Reading Comprehension ◽  
Question Answering ◽  
State Of The Art ◽  
Attention Mechanism ◽  
Dialogue Systems ◽  
Question Generation ◽  
Multi Stage ◽  
Art Methods ◽  
Relevant Context ◽  
Automatic Question Generation

Automatic question generation can benefit many applications ranging from dialogue systems to reading comprehension. While questions are often asked with respect to long documents, there are many challenges with modeling such long documents. Many existing techniques generate questions by effectively looking at one sentence at a time, leading to questions that are easy and not reflective of the human process of question generation. Our goal is to incorporate interactions across multiple sentences to generate realistic questions for long documents. In order to link a broad document context to the target answer, we represent the relevant context via a multi-stage attention mechanism, which forms the foundation of a sequence to sequence model. We outperform state-of-the-art methods on question generation on three question-answering datasets - SQuAD, MS MARCO and NewsQA. 1

Using Question Generation to Improve Reading Comprehension for Middle‐Grade Students

2020 ◽  
Vol 64 (3) ◽  
pp. 311-322
Author(s):  
Elizabeth A. Stevens ◽  
Christy S. Murray ◽  
Sarah Fishstrom ◽  
Sharon Vaughn
Keyword(s):  
Reading Comprehension ◽  
Middle Grade ◽  
Question Generation ◽  
Middle Grade Students

scholarly journals A Multi-Agent Communication Framework for Question-Worthy Phrase Extraction and Question Generation

2019 ◽  
Vol 33 ◽  
pp. 7168-7175 ◽  
Author(s):  
Siyuan Wang ◽  
Zhongyu Wei ◽  
Zhihao Fan ◽  
Yang Liu ◽  
Xuanjing Huang
Keyword(s):  
Reading Comprehension ◽  
Message Passing ◽  
Question Generation ◽  
Agent Communication ◽  
Communication Framework ◽  
Two Agents ◽  
Phrase Extraction ◽  
Multi Agent ◽  
Specific Fragment ◽  
Single Question

Question generation aims to produce questions automatically given a piece of text as input. Existing research follows a sequence-to-sequence fashion that constructs a single question based on the input. Considering each question usually focuses on a specific fragment of the input, especially in the scenario of reading comprehension, it is reasonable to identify the corresponding focus before constructing the question. In this paper, we propose to identify question-worthy phrases first and generate questions with the assistance of these phrases. We introduce a multi-agent communication framework, taking phrase extraction and question generation as two agents, and learn these two tasks simultaneously via message passing mechanism. The results of experiments show the effectiveness of our framework: we can extract question-worthy phrases, which are able to improve the performance of question generation. Besides, our system is able to extract more than one question worthy phrases and generate multiple questions accordingly.

scholarly journals Answer-Aware Question Generation from Tabular and Textual Data using T5

2021 ◽  
Vol 16 (18) ◽  
pp. 256
Author(s):  
Saichandra Pandraju ◽  
Sakthi Ganesh Mahalingam
Keyword(s):  
Systematic Approach ◽  
Structured Data ◽  
Single Model ◽  
Question Generation ◽  
Textual Data ◽  
Knowledge Graphs ◽  
End To End ◽  
Automatic Question Generation

Automatic Question Generation (AQG) systems are applied in a myriad of domains to generate questions from sources such as documents, images, knowledge graphs to name a few. With the rising interest in such AQG systems, it is equally important to recognize structured data like tables while generating questions from documents. In this paper, we propose a single model architecture for question generation from tables along with text using “Text-to-Text Transfer Transformer” (T5) - a fully end-to-end model which does not rely on any intermediate planning steps, delexicalization, or copy mechanisms. We also present our systematic approach in modifying the ToTTo dataset, release the augmented dataset as TabQGen along with the scores achieved using T5 as a baseline to aid further research.

scholarly journals Implementing online question generation to foster reading comprehension

2012 ◽  
Vol 28 (7) ◽  
Author(s):  
Hui-Chin Yeh ◽  
Pei-Yi Lai
Keyword(s):  
College Students ◽  
Reading Comprehension ◽  
Peer Assessment ◽  
Critical Factors ◽  
Generation System ◽  
Question Generation ◽  
Similar Question ◽  
English Major ◽  
Main Ideas ◽  
Positive Effect

<blockquote>Many studies have concluded that question generation has a positive effect on students' reading comprehension. However, few studies have delineated how students generate questions from a text and what processes are involved in question generation. This study aims to investigate how the question generation processes improve students' reading comprehension, using an online question generation system including the organisation, composition and peer assessment modules. 19 out of 106 non-English major college students were recruited as participants. They were required to complete question generation tasks in the organisation, composition and peer assessment modules. Students' scores on the pre- and post-tests, action logs in the online question generation system, and interview transcripts were collected and analysed. In a micro view, results of this study indicated that college students who showed more progress in reading comprehension demonstrated similar question generation patterns. In the organisation module, those who made more progress had a higher frequency of adding new vocabulary, sentences, and main ideas and editing their previously organised information. In the composition module, they had a higher frequency in reviewing the previously organised information from a text to generate questions and in editing the organised information. In the peer assessment module, those who showed more progress were much more active in viewing peers' questions, providing comments on peers' questions, reading and responding to peers' comments on the questions. In a macro view, the intensive engagement and the actions of editing to retrieve the organised information to compose the online questions and reviewing peers' questions online were found to be critical factors for enhancing students' reading comprehension.</blockquote>

Sign in / Sign up

Export Citation Format

Share Document