English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Question answering (QA) models for reading comprehension have achievedhuman-level accuracy on in-distribution test sets. However, they have beendemonstrated to lack robustness to challenge sets, whose distribution isdifferent from that of training sets. Existing data augmentation methodsmitigate this problem by simply augmenting training sets with syntheticexamples sampled from the same distribution as the challenge sets. However,these methods assume that the distribution of a challenge set is known apriori, making them less applicable to unseen challenge sets. In this study, wefocus on question-answer pair generation (QAG) to mitigate this problem. Whilemost existing QAG methods aim to improve the quality of synthetic examples, weconjecture that diversity-promoting QAG can mitigate the sparsity of trainingsets and lead to better robustness. We present a variational QAG model thatgenerates multiple diverse QA pairs from a paragraph. Our experiments show thatour method can improve the accuracy of 12 challenge sets, as well as thein-distribution accuracy. Our code and data are available athttps://github.com/KazutoshiShinoda/VQAG.

Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation