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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recent advances in open-domain question answering (ODQA) have demonstratedimpressive accuracy on standard Wikipedia style benchmarks. However, it is lessclear how robust these models are and how well they perform when applied toreal-world applications in drastically different domains. While there has beensome work investigating how well ODQA models perform when tested forout-of-domain (OOD) generalization, these studies have been conducted onlyunder conservative shifts in data distribution and typically focus on a singlecomponent (ie. retrieval) rather than an end-to-end system. In response, wepropose a more realistic and challenging domain shift evaluation setting and,through extensive experiments, study end-to-end model performance. We find thatnot only do models fail to generalize, but high retrieval scores often stillyield poor answer prediction accuracy. We then categorize different types ofshifts and propose techniques that, when presented with a new dataset, predictif intervention methods are likely to be successful. Finally, using insightsfrom this analysis, we propose and evaluate several intervention methods whichimprove end-to-end answer F1 score by up to 24 points.

To Adapt or to Annotate: Challenges and Interventions for Domain Adaptation in Open-Domain Question Answering