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

Many approaches to Natural Language Processing (NLP) tasks often treat themas single-step problems, where an agent receives an instruction, executes it,and is evaluated based on the final outcome. However, human language isinherently interactive, as evidenced by the back-and-forth nature of humanconversations. In light of this, we posit that human-AI collaboration shouldalso be interactive, with humans monitoring the work of AI agents and providingfeedback that the agent can understand and utilize. Further, the AI agentshould be able to detect when it needs additional information and proactivelyask for help. Enabling this scenario would lead to more natural, efficient, andengaging human-AI collaborations.  In this work, we explore these directions using the challenging task definedby the IGLU competition, an interactive grounded language understanding task ina MineCraft-like world. We explore multiple types of help players can give tothe AI to guide it and analyze the impact of this help in AI behavior,resulting in performance improvements.

Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback