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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Clarifying the underlying user information need by asking clarifyingquestions is an important feature of modern conversational search system.However, evaluation of such systems through answering prompted clarifyingquestions requires significant human effort, which can be time-consuming andexpensive. In this paper, we propose a conversational User Simulator, calledUSi, for automatic evaluation of such conversational search systems. Given adescription of an information need, USi is capable of automatically answeringclarifying questions about the topic throughout the search session. Through aset of experiments, including automated natural language generation metrics andcrowdsourcing studies, we show that responses generated by USi are both inlinewith the underlying information need and comparable to human-generated answers.Moreover, we make the first steps towards multi-turn interactions, whereconversational search systems asks multiple questions to the (simulated) userwith a goal of clarifying the user need. To this end, we expand on currentlyavailable datasets for studying clarifying questions, i.e., Qulac and ClariQ,by performing a crowdsourcing-based multi-turn data acquisition. We show thatour generative, GPT2-based model, is capable of providing accurate and naturalanswers to unseen clarifying questions in the single-turn setting and discusscapabilities of our model in the multi-turn setting. We provide the code, data,and the pre-trained model to be used for further research on the topic.

Evaluating Mixed-initiative Conversational Search Systems via User Simulation