Question Answering and Question Generation as Dual Tasks

Tang, Duyu; Duan, Nan; Qin, Tao; Yan, Zhao; Zhou, Ming

doi:10.48550/arxiv.1706.02027

Cited by 116 publications

(53 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One may expect that Narra-tiveQA could also be used for QAG tasks. In fact, a coupe of recent works use this dataset and train a network by combining a QG module and a QA module together with a reinforcement learning approach (Tang et al, 2017). For example, Wang et al (2017) use the QA result to reward the QG module then jointly train the two sub-systems.…”

Section: Related Workmentioning

confidence: 99%

It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books

Wang¹,

Wu²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Existing question answering (QA) datasets are created mainly for the application of having AI to be able to answer questions asked by humans. But in educational applications, teachers and parents sometimes may not know what questions they should ask a child that can maximize their language learning results. With a newly released book QA dataset (FairytaleQA), which educational experts labeled on 46 fairytale storybooks for early childhood readers, we developed an automated QA generation model architecture for this novel application. Our model (1) extracts candidate answers from a given storybook passage through carefully designed heuristics based on a pedagogical framework; (2) generates appropriate questions corresponding to each extracted answer using a language model; and, (3) uses another QA model to rank top QA-pairs. Automatic and human evaluations show that our model outperforms baselines. We also demonstrate that our method can help with the scarcity issue of the children's book QA dataset via data augmentation on 200 unlabeled storybooks.

show abstract

Section: Related Workmentioning

confidence: 99%

It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books

Wang¹,

Wu²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Iterative backtranslation (IBT) (Hoang et al 2018;Guo et al 2021) is an extension of back-translation, in which forward and backward models are trained together to generate pseudo parallel instances with each other. A similar line of studies (Su, Huang, and Chen 2020;Tang et al 2017) adopts dual learning, which incorporates the inference process of both models into training via reinforcement learning. IBT and dual learning are based on the same idea, to jointly solve tasks with duality used in machine translation.…”

Section: Related Workmentioning

confidence: 99%

Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation

Liu¹,

Luo²,

Okazaki³

2021

Preprint

View full text Add to dashboard Cite

Logical Natural Language Generation, i.e., generating textual descriptions that can be logically entailed by a structured table, has been a challenge due to the low fidelity of the generation. Chen et al. (2020b) have addressed this problem by annotating interim logical programs to control the generation contents and semantics, and presented the task of table-aware logical form to text (Logic2text) generation. However, although table instances are abundant in the real world, logical forms paired with textual descriptions require costly human annotation work, which limits the performance of neural models.To mitigate this, we propose topic-conditioned data augmentation (TopicDA), which utilizes GPT-2 to generate unpaired logical forms and textual descriptions directly from tables. We further introduce logical form generation (LG), a dual task of Logic2text that requires generating a valid logical form based on a text description of a table. We also propose a semisupervised learning approach to jointly train a Logic2text and an LG model with both labeled and augmented data. The two models benefit from each other by providing extra supervision signals through back-translation. Experimental results on the Logic2text dataset and the LG task demonstrate that our approach can effectively utilize the augmented data and outperform supervised baselines by a substantial margin.

show abstract

“…Question generation has the potential to improve the training of QA systems (Du and Cardie, 2018;Tang et al, 2017), and help chatbots start a conversation with human users (Mostafazadeh et al, 2016). However, the well-designed templates in rule-based lack diversity, and they do not generalize to a new domain (Ali et al, 2010).…”

Section: Related Workmentioning

confidence: 99%

How to Build Robust FAQ Chatbot with Controllable Question Generator?

Pan¹,

Ma²,

Pflugfelder³

et al. 2021

Preprint

View full text Add to dashboard Cite

Many unanswerable adversarial questions fool the question-answer (QA) system with some plausible answers. Building a robust, frequently asked questions (FAQ) chatbot needs a large amount of diverse adversarial examples.Recent question generation methods are ineffective at generating many high-quality and diverse adversarial question-answer pairs from unstructured text. We propose the diversity controllable semantically valid adversarial attacker (DCSA), a high-quality, diverse, controllable method to generate standard and adversarial samples with a semantic graph. The fluent and semantically generated QA pairs fool our passage retrieval model successfully. After that, we conduct a study on the robustness and generalization of the QA model with generated QA pairs among different domains. We find that the generated data set improves the generalizability of the QA model to the new target domain and the robustness of the QA model to detect unanswerable adversarial questions.

show abstract

Question Answering and Question Generation as Dual Tasks

Cited by 116 publications

References 18 publications

It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books

It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books

Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation

How to Build Robust FAQ Chatbot with Controllable Question Generator?

Contact Info

Product

Resources

About