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

We introduce the StatCan Dialogue Dataset consisting of 19,379 conversationturns between agents working at Statistics Canada and online users looking forpublished data tables. The conversations stem from genuine intents, are held inEnglish or French, and lead to agents retrieving one of over 5000 complex datatables. Based on this dataset, we propose two tasks: (1) automatic retrieval ofrelevant tables based on a on-going conversation, and (2) automatic generationof appropriate agent responses at each turn. We investigate the difficulty ofeach task by establishing strong baselines. Our experiments on a temporal datasplit reveal that all models struggle to generalize to future conversations, aswe observe a significant drop in performance across both tasks when we movefrom the validation to the test set. In addition, we find that responsegeneration models struggle to decide when to return a table. Considering thatthe tasks pose significant challenges to existing models, we encourage thecommunity to develop models for our task, which can be directly used to helpknowledge workers find relevant tables for live chat users.

The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents