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

Incorporating external knowledge into the response generation process isessential to building more helpful and reliable dialog agents. However,collecting knowledge-grounded conversations is often costly, calling for abetter pre-trained model for grounded dialog generation that generalizes wellw.r.t. different types of knowledge. In this work, we propose KPT(Keyword-guided Pre-Training), a novel self-supervised pre-training method forgrounded dialog generation without relying on extra knowledge annotation.Specifically, we use a pre-trained language model to extract the most uncertaintokens in the dialog as keywords. With these keywords, we construct two kindsof knowledge and pre-train a knowledge-grounded response generation model,aiming at handling two different scenarios: (1) the knowledge should befaithfully grounded; (2) it can be selectively used. For the former, thegrounding knowledge consists of keywords extracted from the response. For thelatter, the grounding knowledge is additionally augmented with keywordsextracted from other utterances in the same dialog. Since the knowledge isextracted from the dialog itself, KPT can be easily performed on a large volumeand variety of dialogue data. We considered three data sources (open-domain,task-oriented, conversational QA) with a total of 2.5M dialogues. We conductextensive experiments on various few-shot knowledge-grounded generation tasks,including grounding on dialog acts, knowledge graphs, persona descriptions, andWikipedia passages. Our comprehensive experiments and analyses demonstrate thatKPT consistently outperforms state-of-the-art methods on these tasks withdiverse grounding knowledge.

KPT: Keyword-guided Pre-training for Grounded Dialog Generation