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

In conversational search, which aims to retrieve passages containingessential information, queries suffer from high dependency on the precedingdialogue context. Therefore, reformulating conversational queries intostandalone forms is essential for the effective utilization of off-the-shelfretrievers. Previous methodologies for conversational query search frequentlydepend on human-annotated gold labels. However, these manually crafted queriesoften result in sub-optimal retrieval performance and require high collectioncosts. In response to these challenges, we propose Iterative ConversationalQuery Reformulation (IterCQR), a methodology that conducts query reformulationwithout relying on human oracles. IterCQR iteratively trains the QR model bydirectly leveraging signal from information retrieval (IR) as a reward. Ourproposed IterCQR method shows state-of-the-art performance on two datasets,demonstrating its effectiveness on both sparse and dense retrievers. Notably,IterCQR exhibits robustness in domain-shift, low-resource, and topic-shiftscenarios.

IterCQR: Iterative Conversational Query Reformulation without Human Supervision