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

Referential ambiguities arise in dialogue when a referring expression doesnot uniquely identify the intended referent for the addressee. Addresseesusually detect such ambiguities immediately and work with the speaker to repairit using meta-communicative, Clarificational Exchanges (CE): a ClarificationRequest (CR) and a response. Here, we argue that the ability to generate andrespond to CRs imposes specific constraints on the architecture and objectivefunctions of multi-modal, visually grounded dialogue models. We use the SIMMC2.0 dataset to evaluate the ability of different state-of-the-art modelarchitectures to process CEs, with a metric that probes the contextual updatesthat arise from them in the model. We find that language-based models are ableto encode simple multi-modal semantic information and process some CEs,excelling with those related to the dialogue history, whilst multi-modal modelscan use additional learning objectives to obtain disentangled objectrepresentations, which become crucial to handle complex referential ambiguitiesacross modalities overall.

'What are you referring to?' Evaluating the Ability of Multi-Modal Dialogue Models to Process Clarificational Exchanges