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

Harvesting question-answer (QA) pairs from customer service chatlog in thewild is an efficient way to enrich the knowledge base for customer servicechatbots in the cold start or continuous integration scenarios. Prior workattempts to obtain 1-to-1 QA pairs from growing customer service chatlog, whichfails to integrate the incomplete utterances from the dialog context forcomposite QA retrieval. In this paper, we propose N-to-N QA extraction task inwhich the derived questions and corresponding answers might be separated acrossdifferent utterances. We introduce a suite of generative/discriminative taggingbased methods with end-to-end and two-stage variants that perform well on 5customer service datasets and for the first time setup a benchmark for N-to-NDialogQAE with utterance and session level evaluation metrics. With a deep diveinto extracted QA pairs, we find that the relations between and inside the QApairs can be indicators to analyze the dialogue structure, e.g. informationseeking, clarification, barge-in and elaboration. We also show that theproposed models can adapt to different domains and languages, and reduce thelabor cost of knowledge accumulation in the real-world product dialogueplatform.

DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog