Improving Neural Question Generation using World Knowledge

Gupta, Deepak; Suleman, Kaheer; Adada, Mahmoud; McNamara, Andrew; Harris, Justin A.

doi:10.48550/arxiv.1909.03716

Cited by 2 publications

(3 citation statements)

References 18 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, because graph neural networks (Kipf et al 2016;Gilmer et al 2017;Hamilton et al 2017) have made great progress in representation learning, many researchers use it to capture the relationship between words in context (Fan et al 2019;Huang et al 2020). Some researchers have also begun to explore the role of GNNs in the QG task.…”

Section: Related Workmentioning

confidence: 99%

Entity Guided Question Generation with Contextual Structure and Sequence Information Capturing

Huang

et al. 2021

AAAI

View full text Add to dashboard Cite

Question generation is a challenging task and has attracted widespread attention in recent years. Although previous studies have made great progress, there are still two main shortcomings: First, previous work did not simultaneously capture the sequence information and structure information hidden in the context, which results in poor results of the generated questions. Second, the generated questions cannot be answered by the given context. To tackle these issues, we propose an entity guided question generation model with contextual structure information and sequence information capturing. We use a Graph Convolutional Network and a Bidirectional Long Short Term Memory Network to capture the structure information and sequence information of the context, simultaneously. In addition, to improve the answerability of the generated questions, we use an entity-guided approach to obtain question type from the answer, and jointly encode the answer and question type. Both automatic and manual metrics show that our model can generate comparable questions with state-of-the-art models. Our code is available at https://github.com/VISLANG-Lab/EGSS.

show abstract

Section: Related Workmentioning

confidence: 99%

Entity Guided Question Generation with Contextual Structure and Sequence Information Capturing

Huang

et al. 2021

AAAI

View full text Add to dashboard Cite

show abstract

“…• SeqCopyNet [54], NQG++ [53], AFPA [42], seq2seq+z+c+GAN [50], and s2sa-at-mp-gsa [52]: answer-aware neural question generation models based on Seq2Seq framework. • NQG-Knowledge [16], DLPH [12]: auxiliary-informationenhanced question generation models with extra inputs such as knowledge or difficulty. • Self-training-EE [38], BERT-QG-QAP [51], NQG-LM [55],…”

Section: Evaluating Acs-aware Question Generationmentioning

confidence: 99%

“…[22] identifies the content shared by a given question and answer pair as an aspect, and learns an aspect-based question generation model. [16] incorporates knowledge base information to ask questions. Compared with these works, our work doesn't require extra labeling or training overhead to get the training dataset.…”

Section: Related Workmentioning

confidence: 99%

Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus

Liu

Wei

Niu

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

The ability to ask questions is important in both human and machine intelligence. Learning to ask questions helps knowledge acquisition, improves question-answering and machine reading comprehension tasks, and helps a chatbot to keep the conversation flowing with a human. Existing question generation models are ineffective at generating a large amount of high-quality question-answer pairs from unstructured text, since given an answer and an input passage, question generation is inherently a one-to-many mapping. In this paper, we propose Answer-Clue-Style-aware Question Generation (ACS-QG), which aims at automatically generating high-quality and diverse question-answer pairs from unlabeled text corpus at scale by imitating the way a human asks questions. Our system consists of: i) an information extractor, which samples from the text multiple types of assistive information to guide question generation; ii) neural question generators, which generate diverse and controllable questions, leveraging the extracted assistive information; and iii) a neural quality controller, which removes low-quality generated data based on text entailment. We compare our question generation models with existing approaches and resort to voluntary human evaluation to assess the quality of the generated question-answer pairs. The evaluation results suggest that our system dramatically outperforms state-of-the-art neural question generation models in terms of the generation quality, while being scalable in the meantime. With models trained on a relatively smaller amount of data, we can generate 2.8 million quality-assured question-answer pairs from a million sentences found in Wikipedia.

show abstract

Improving Neural Question Generation using World Knowledge

Cited by 2 publications

References 18 publications

Entity Guided Question Generation with Contextual Structure and Sequence Information Capturing

Entity Guided Question Generation with Contextual Structure and Sequence Information Capturing

Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus

Contact Info

Product

Resources

About