Leveraging Context Information for Natural Question Generation

Song, Linfeng; Wang, Zhiguo; Hamza, Wael; Zhang, Yue; Gildea, Daniel

doi:10.18653/v1/n18-2090

Cited by 134 publications

(130 citation statements)

References 13 publications

Supporting

Mentioning

121

Contrasting

Order By: Relevance

“…• PCFG-Trans [12] is a rule-based system that generates a question based on a given answer word span. • MPQG [31] proposed a Seq2Seq model that matches the answer with the passage before generating the question. • SeqCopyNet [43] proposed a method to improve the copying mechanism in Seq2Seq models by copying not only a single word but a sequence of words from the input sentence.…”

Section: Datasets Metrics and Baselinesmentioning

confidence: 99%

Learning to Generate Questions by LearningWhat not to Generate

Liu

Zhao

Niu

et al. 2019

The World Wide Web Conference

View full text Add to dashboard Cite

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.

show abstract

Section: Datasets Metrics and Baselinesmentioning

confidence: 99%

Learning to Generate Questions by LearningWhat not to Generate

Liu

Zhao

Niu

et al. 2019

The World Wide Web Conference

View full text Add to dashboard Cite

show abstract

“…They adopt a BIO tagging scheme to incorporate the answer position information as learned embedding features in Seq2Seq learning. Song et al (2018) explicitly model the information between answer and sentence with a multiperspective matching model. Kim et al (2019) also focus on the answer information and proposed an answer-separated Seq2Seq model by masking the answer with special tokens.…”

Section: Related Workmentioning

confidence: 99%

Improving Question Generation With to the Point Context

Li¹,

Gao²,

Bing³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Question generation (QG) is the task of generating a question from a reference sentence and a specified answer within the sentence. A major challenge in QG is to identify answer-relevant context words to finish the declarative-to-interrogative sentence transformation. Existing sequence-to-sequence neural models achieve this goal by proximity-based answer position encoding under the intuition that neighboring words of answers are of high possibility to be answer-relevant. However, such intuition may not apply to all cases especially for sentences with complex answerrelevant relations. Consequently, the performance of these models drops sharply when the relative distance between the answer fragment and other non-stop sentence words that also appear in the ground truth question increases. To address this issue, we propose a method to jointly model the unstructured sentence and the structured answer-relevant relation (extracted from the sentence in advance) for question generation. Specifically, the structured answer-relevant relation acts as the to the point context and it thus naturally helps keep the generated question to the point, while the unstructured sentence provides the full information. Extensive experiments show that to the point context helps our question generation model achieve significant improvements on several automatic evaluation metrics. Furthermore, our model is capable of generating diverse questions for a sentence which conveys multiple relations of its answer fragment.

show abstract

“…We retained the same values for most hyperparameters in our experiments as the baseline system (Song et al, 2018).…”

Section: Baseline and Settingsmentioning

confidence: 99%

Generating Highly Relevant Questions

Qiu¹,

Xiong

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

The neural seq2seq based question generation (QG) is prone to generating generic and undiversified questions that are poorly relevant to the given passage and target answer. In this paper, we propose two methods to address the issue.(1) By a partial copy mechanism, we prioritize words that are morphologically close to words in the input passage when generating questions;(2) By a QA-based reranker, from the n-best list of question candidates, we select questions that are preferred by both the QA and QG model. Experiments and analyses demonstrate that the proposed two methods substantially improve the relevance of generated questions to passages and answers.

show abstract

Leveraging Context Information for Natural Question Generation

Cited by 134 publications

References 13 publications

Learning to Generate Questions by LearningWhat not to Generate

Learning to Generate Questions by LearningWhat not to Generate

Improving Question Generation With to the Point Context

Generating Highly Relevant Questions

Contact Info

Product

Resources

About