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

Factual correctness is often the limiting factor in practical applications ofnatural language generation in high-stakes domains such as healthcare. Anessential requirement for maintaining factuality is the ability to deal withrare tokens. This paper focuses on rare tokens that appear in both the sourceand the reference sequences, and which, when missed during generation, decreasethe factual correctness of the output text. For high-stake domains that arealso knowledge-rich, we show how to use knowledge to (a) identify which raretokens that appear in both source and reference are important and (b) uplifttheir conditional probability. We introduce the ``utilization rate'' thatencodes knowledge and serves as a regularizer by maximizing the marginalprobability of selected tokens. We present a study in a knowledge-rich domainof healthcare, where we tackle the problem of generating after-visit careinstructions based on patient-doctor dialogues. We verify that, in our dataset,specific medical concepts with high utilization rates are underestimated byconventionally trained sequence-to-sequence models. We observe that correctingthis with our approach to knowledge injection reduces the uncertainty of themodel as well as improves factuality and coherence without negatively impactingfluency.

Injecting knowledge into language generation: a case study in auto-charting after-visit care instructions from medical dialogue