Machine Comprehension by Text-to-Text Neural Question Generation

Yuan, Xingdi; Wang, Tong; Gülçehre, Çağlar; Sordoni, Alessandro; Bachman, Philip; Zhang, Saizheng; Subramanian, Sandeep; Trischler, Adam

doi:10.18653/v1/w17-2603

Cited by 143 publications

(107 citation statements)

References 39 publications

(61 reference statements)

Supporting

Mentioning

105

Contrasting

Unclassified

Order By: Relevance

“…Purely relying on Seq2Seq model may not be able to learn such a one-to-many mapping [9]. To resolve this issue, recent works assume the aspect is known when generating a question [16,31,32,38,42] or can be detected by a third-party pipeline [7]. [42] enriches the sequence-to-sequence model with answer position indicator to indicate if the current word is an answer word or not, and further incorporates copy mechanism to copy words from the context when generating a question.…”

Section: Related Workmentioning

confidence: 99%

“…As a dual task of question answering, question generation based on a text passage and a given answer has attracted much attention in recent years. One of the key applications of question generation is to automatically produce question-answer pairs to enhance machine reading comprehension systems [8,34,35,38]. Another application is generating practice exercises and assessments for educational purposes [4,12,13].…”

Section: Introductionmentioning

confidence: 99%

“…These models formulate the question generation task as a sequence-to-sequence (Seq2Seq) neural learning problem, where different types of encoders and decoders have been designed. Like many other text generation tasks, the copying or pointer mechanism [11] is also widely adopted in question generation to handle the copy phenomenon between input passages and output questions, e.g., [16,31,32,38,42]. However, we point out that a common limitation that hurdles question generation models mainly use copying mechanisms to handle out-of-vocabulary (OOV) issues, and fail to mark a clear boundary between the set of question words that should be directly copied from the input text and those that should be generated instead.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

“…This need to generate multiple questions for a sentence motivates our use of an answer signal. The model described by Yuan et al (2017) also uses an answer signal feature. However, by combining it with additional features and the question specific sentence encoder our model achieves better results, as we show in Section 3.…”

Section: Feature Supervisionmentioning

confidence: 99%

Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features

Harrison¹,

Walker²

2018

Proceedings of the 11th International Conference on Natural Language Generation

View full text Add to dashboard Cite

Question Generation is the task of automatically creating questions from textual input. In this work we present a new Attentional Encoder-Decoder Recurrent Neural Network model for automatic question generation. Our model incorporates linguistic features and an additional sentence embedding to capture meaning at both sentence and word levels. The linguistic features are designed to capture information related to named entity recognition, word case, and entity coreference resolution. In addition our model uses a copying mechanism and a special answer signal that enables generation of numerous diverse questions on a given sentence. Our model achieves state of the art results of 19.98 Bleu 4 on a benchmark Question Generation dataset, outperforming all previously published results by a significant margin. A human evaluation also shows that the added features improve the quality of the generated questions.

show abstract

“…Questions are usually asked to access knowledge of others or direct one's own information-seeking behavior. According to authors in [27], the incentives to teach machines to ask questions are:…”

Section: Joint Model Based Training To Improve Performance Of Neumentioning

confidence: 99%

Open-Domain Neural Conversational Agents: The Step Towards Artificial General Intelligence

Arsovski¹,

Wong²,

Cheok³

2018

ijacsa

View full text Add to dashboard Cite

Abstract-Development of conversational agents started half century ago and since then it has transformed into a technology that is accessible in various aspects in everyday life. This paper presents a survey current state-of-the-art in the open domain neural conversational agent research and future research directions towards Artificial General Intelligence (AGI) creation. In order to create a conversational agent which is able to pass the Turing Test, numerous research efforts are focused on open-domain dialogue system. This paper will present latest research in domain of Neural Network reasoning and logical association, sentiment analysis and real-time learning approaches applied to open domain neural conversational agents. As an effort to provide future research directions, current cuttingedge approaches applied to open domain neural conversational agents, current cutting-edge approaches in rationale generation and the state-of-the-art research directions in alternative training methods will be discussed in this paper.

show abstract

Machine Comprehension by Text-to-Text Neural Question Generation

Cited by 143 publications

References 39 publications

Learning to Generate Questions by LearningWhat not to Generate

Learning to Generate Questions by LearningWhat not to Generate

Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features

Open-Domain Neural Conversational Agents: The Step Towards Artificial General Intelligence

Contact Info

Product

Resources

About