Published on Wed Feb 27 2019

Learning to Generate Questions by Learning What not to Generate

Bang Liu, Mingjun Zhao, Di Niu, Kunfeng Lai, Yancheng He, Haojie Wei, Yu Xu

Automatic question generation is an important technique that can improve the training of question answering. Existing neural question generation models are not sufficient mainly due to their inability to properly model the process of how each word in the question is selected. In this paper, we propose our Clue Guided Copy Network for Question Generation (CGC-QG)

0
0
0
Abstract

Automatic question generation is an important technique that can improve the training of question answering, help chatbots to start or continue a conversation with humans, and provide assessment materials for educational purposes. Existing neural question generation models are not sufficient mainly due to their inability to properly model the process of how each word in the question is selected, i.e., whether repeating the given passage or being generated from a vocabulary. In this paper, we propose our Clue Guided Copy Network for Question Generation (CGC-QG), which is a sequence-to-sequence generative model with copying mechanism, yet employing a variety of novel components and techniques to boost the performance of question generation. In CGC-QG, we design a multi-task labeling strategy to identify whether a question word should be copied from the input passage or be generated instead, guiding the model to learn the accurate boundaries between copying and generation. Furthermore, our input passage encoder takes as input, among a diverse range of other features, the prediction made by a clue word predictor, which helps identify whether each word in the input passage is a potential clue to be copied into the target question. The clue word predictor is designed based on a novel application of Graph Convolutional Networks onto a syntactic dependency tree representation of each passage, thus being able to predict clue words only based on their context in the passage and their relative positions to the answer in the tree. We jointly train the clue prediction as well as question generation with multi-task learning and a number of practical strategies to reduce the complexity. Extensive evaluations show that our model significantly improves the performance of question generation and out-performs all previous state-of-the-art neural question generation models by a substantial margin.

Tue Sep 17 2019
Machine Learning
Learning to Generate Questions with Adaptive Copying Neural Networks
Automatic question generation is an important problem in natural language processing. We propose a novel adaptive copying recurrent neural network model to tackle the problem.
0
0
0
Sat Aug 31 2019
Artificial Intelligence
Let's Ask Again: Refine Network for Automatic Question Generation
Refine Network (RefNet) contains two decoders. The second decoder uses a dual attention network which pays attention to both the original passage and the question. In effect, it refines the question generated by the first decoder, thereby making it more correct and complete. The code has been made publicly available on GitHub.
0
0
0
Thu Apr 06 2017
NLP
Neural Question Generation from Text: A Preliminary Study
Automatic question generation aims to generate questions from a text passage. Traditional methods mainly use rigid heuristic rules. We propose to apply the neural encoder-decoder model to generate meaningful and diverse questions from natural language sentences.
0
0
0
Mon Sep 09 2019
Artificial Intelligence
Question Generation by Transformers
A machine learning model was developed to automatically generate questions from Wikipedia passages using transformers. The model was trained on the inverted Stanford Question Answering Dataset (SQuAD), which is a reading comprehension dataset.
1
0
1
Thu Nov 16 2017
NLP
A Generative Approach to Question Answering
Question Answering has come a long way from answer sentence selection to reading and comprehension. Not being able to retain facts and making repetitions are common mistakes that affect the overall legibility of answers. To counter these issues, we employ a copying mechanism and maintenance of coverage vector.
0
0
0
Sun May 24 2020
Machine Learning
A Question Type Driven and Copy Loss Enhanced Frameworkfor Answer-Agnostic Neural Question Generation
0
0
0