Improving Neural Question Generation using Answer Separation

Abstract

Neural question generation (NQG) is the task of generating a question from a given passage with deep neural networks. Previous NQG models suffer from a problem that a significant proportion of the generated questions include words in the question target, resulting in the generation of unintended questions. In this paper, we propose answer-separated seq2seq, which better utilizes the information from both the passage and the target answer. By replacing the target answer in the original passage with a special token, our model learns to identify which interrogative word should be used. We also propose a new module termed keyword-net, which helps the model better capture the key information in the target answer and generate an appropriate question. Experimental results demonstrate that our answer separation method significantly reduces the number of improper questions which include answers. Consequently, our model significantly outperforms previous state-of-the-art NQG models.

arXiv commentThe paper is accepted to AAAI 2019

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• Microsoft COCO Captions: Data Collection and Evaluation Server
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
• Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
• Question Answering and Question Generation as Dual Tasks
• Bilateral Multi-Perspective Matching for Natural Language Sentences
• Learning to Ask: Neural Question Generation for Reading Comprehension
• Pointing the Unknown Words
• Neural Question Generation from Text: A Preliminary Study
• Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
• Entity Commonsense Representation for Neural Abstractive Summarization

Cited by in corpus (5)

• Learning to Generate Questions by Learning What not to Generate
• Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model
• Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering
• Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring
• Improving Neural Question Generation using World Knowledge