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

Visual Word Sense Disambiguation (VWSD) is a multi-modal task that aims toselect, among a batch of candidate images, the one that best entails the targetword's meaning within a limited context. In this paper, we propose amulti-modal retrieval framework that maximally leverages pretrainedVision-Language models, as well as open knowledge bases and datasets. Oursystem consists of the following key components: (1) Gloss matching: apretrained bi-encoder model is used to match contexts with proper senses of thetarget words; (2) Prompting: matched glosses and other textual information,such as synonyms, are incorporated using a prompting template; (3) Imageretrieval: semantically matching images are retrieved from large open datasetsusing prompts as queries; (4) Modality fusion: contextual information fromdifferent modalities are fused and used for prediction. Although our systemdoes not produce the most competitive results at SemEval-2023 Task 1, we arestill able to beat nearly half of the teams. More importantly, our experimentsreveal acute insights for the field of Word Sense Disambiguation (WSD) andmulti-modal learning. Our code is available on GitHub.

HKUST at SemEval-2023 Task 1: Visual Word Sense Disambiguation with Context Augmentation and Visual Assistance