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

Several multi-hop reading comprehension datasets have been proposed toresolve the issue of reasoning shortcuts by which questions can be answeredwithout performing multi-hop reasoning. However, the ability of multi-hopmodels to perform step-by-step reasoning when finding an answer to a comparisonquestion remains unclear. It is also unclear how questions about the internalreasoning process are useful for training and evaluating question-answering(QA) systems. To evaluate the model precisely in a hierarchical manner, wefirst propose a dataset, \textit{HieraDate}, with three probing tasks inaddition to the main question: extraction, reasoning, and robustness. Ourdataset is created by enhancing two previous multi-hop datasets, HotpotQA and2WikiMultiHopQA, focusing on multi-hop questions on date information thatinvolve both comparison and numerical reasoning. We then evaluate the abilityof existing models to understand date information. Our experimental resultsreveal that the multi-hop models do not have the ability to subtract two dateseven when they perform well in date comparison and number subtraction tasks.Other results reveal that our probing questions can help to improve theperformance of the models (e.g., by +10.3 F1) on the main QA task and ourdataset can be used for data augmentation to improve the robustness of themodels.

How Well Do Multi-hop Reading Comprehension Models Understand Date Information?