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

Prediction over event sequences is critical for many real-world applicationsin Information Retrieval and Natural Language Processing. Future EventGeneration (FEG) is a challenging task in event sequence prediction because itrequires not only fluent text generation but also commonsense reasoning tomaintain the logical coherence of the entire event story. In this paper, wepropose a novel explainable FEG framework, Coep. It highlights and integratestwo types of event knowledge, sequential knowledge of direct event-eventrelations and inferential knowledge that reflects the intermediate characterpsychology between events, such as intents, causes, reactions, whichintrinsically pushes the story forward. To alleviate the knowledge forgettingissue, we design two modules, Im and Gm, for each type of knowledge, which arecombined via prompt tuning. First, Im focuses on understanding inferentialknowledge to generate commonsense explanations and provide a soft prompt vectorfor Gm. We also design a contrastive discriminator for better generalizationability. Second, Gm generates future events by modeling direct sequentialknowledge with the guidance of Im. Automatic and human evaluation demonstratethat our approach can generate more coherent, specific, and logical futureevents.

What Makes the Story Forward? Inferring Commonsense Explanations as Prompts for Future Event Generation