Learning to Generate Questions by Learning to Recover Answer-containing Sentences

Machine Reading Comprehension (MRC) is a challenging task and hot topic in Natural Language Processing. The goal of this field is to develop systems for answering the questions regarding a given context. In this paper, we present a comprehensive survey on diverse aspects of MRC systems, including their approaches, structures, input/outputs, and research novelties. We illustrate the recent trends in this field based on a review of 241 papers published during 2016–2020. Our investigation demonstrated that the focus of research has changed in recent years from answer extraction to answer generation, from single- to multi-document reading comprehension, and from learning from scratch to using pre-trained word vectors. Moreover, we discuss the popular datasets and the evaluation metrics in this field. The paper ends with an investigation of the most-cited papers and their contributions.

show abstract

“…2019), more attention has been paid to this issue (Back et al . 2020; Liu et al . 2020a; Zhang et al .…”

Section: Future Trends and Opportunitiesmentioning

confidence: 99%

A Survey on Machine Reading Comprehension Systems

2022

View full text Add to dashboard Cite

show abstract

“…However, their human evaluation centered around question correctness and fluency rather than relevance of answer selection. Similar follow-up studies also fail to explicitly ask annotators whether or not the extracted answers, and subsequent generated questions, were relevant to the broader topic of the context passage (Willis et al, 2019;Cui et al, 2021;Du and Cardie, 2018;Alberti et al, 2019;Back et al, 2021).…”

Section: Related Work and Backgroundmentioning

confidence: 99%

A Feasibility Study of Answer-Unaware Question Generation for Education

Dugan¹,

Miltsakaki²,

Upadhyay³

et al. 2022

Findings of the Association for Computational Linguistics: ACL 2022

View full text Add to dashboard Cite

We conduct a feasibility study into the applicability of answer-agnostic question generation models to textbook passages. We show that a significant portion of errors in such systems arise from asking irrelevant or uninterpretable questions and that such errors can be ameliorated by providing summarized input. We find that giving these models human-written summaries instead of the original text results in a significant increase in acceptability of generated questions (33% → 83%) as determined by expert annotators. We also find that, in the absence of human-written summaries, automatic summarization can serve as a good middle ground.

show abstract

“…We also compare our pre-training to that of the data augmentation (Mao et al, 2021a;Oguz et al, 2021). We generate 'questionanswer' pairs from a Wikipedia dump using a question and answer generation model trained on the NQ dataset using ASGen approach (Back et al, 2021). The model is further trained after the pretraining by this augmented data for 15,000 steps before fine-tuning.…”

Section: Effectiveness Of Emss Pre-trainingmentioning

confidence: 99%

You Only Need One Model for Open-domain Question Answering

Lee¹,

Kedia²,

Lee³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recent works for Open-domain Question Answering refer to an external knowledge base using a retriever model, optionally rerank the passages with a separate reranker model and generate an answer using an another reader model. Despite performing related tasks, the models have separate parameters and are weakly-coupled during training. In this work, we propose casting the retriever and the reranker as hard-attention mechanisms applied sequentially within the transformer architecture and feeding the resulting computed representations to the reader. In this singular model architecture the hidden representations are progressively refined from the retriever to the reranker to the reader, which is more efficient use of model capacity and also leads to better gradient flow when we train it in an end-to-end manner. We also propose a pretraining methodology to effectively train this architecture. We evaluate our model on Natural Questions and TriviaQA open datasets and for a fixed parameter budget, our model outperforms the previous state-of-the-art model by 1.0 and 0.7 exact match scores.

show abstract

Learning to Generate Questions by Learning to Recover Answer-containing Sentences

Cited by 13 publications

References 24 publications

A Survey on Machine Reading Comprehension Systems

A Survey on Machine Reading Comprehension Systems

A Feasibility Study of Answer-Unaware Question Generation for Education

You Only Need One Model for Open-domain Question Answering

Contact Info

Product

Resources

About