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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Tracking entities throughout a procedure described in a text is challengingdue to the dynamic nature of the world described in the process. Firstly, wepropose to formulate this task as a question answering problem. This enables usto use pre-trained transformer-based language models on other QA benchmarks byadapting those to the procedural text understanding. Secondly, since thetransformer-based language models cannot encode the flow of events bythemselves, we propose a Time-Stamped Language Model~(TSLM model) to encodeevent information in LMs architecture by introducing the timestamp encoding.Our model evaluated on the Propara dataset shows improvements on the publishedstate-of-the-art results with a $3.1\%$ increase in F1 score. Moreover, ourmodel yields better results on the location prediction task on the NPN-Cookingdataset. This result indicates that our approach is effective for proceduraltext understanding in general.

Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Events