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

Tags are pivotal in facilitating the effective distribution of multimediacontent in various applications in the contemporary Internet era, such assearch engines and recommendation systems. Recently, large language models(LLMs) have demonstrated impressive capabilities across a wide range of tasks.In this work, we propose TagGPT, a fully automated system capable of tagextraction and multimodal tagging in a completely zero-shot fashion. Our coreinsight is that, through elaborate prompt engineering, LLMs are able to extractand reason about proper tags given textual clues of multimodal data, e.g., OCR,ASR, title, etc. Specifically, to automatically build a high-quality tag setthat reflects user intent and interests for a specific application, TagGPTpredicts large-scale candidate tags from a series of raw data via promptingLLMs, filtered with frequency and semantics. Given a new entity that needstagging for distribution, TagGPT introduces two alternative options forzero-shot tagging, i.e., a generative method with late semantic matching withthe tag set, and another selective method with early matching in prompts. It iswell noticed that TagGPT provides a system-level solution based on a modularframework equipped with a pre-trained LLM (GPT-3.5 used here) and a sentenceembedding model (SimCSE used here), which can be seamlessly replaced with anymore advanced one you want. TagGPT is applicable for various modalities of datain modern social media and showcases strong generalization ability to a widerange of applications. We evaluate TagGPT on publicly available datasets, i.e.,Kuaishou and Food.com, and demonstrate the effectiveness of TagGPT compared toexisting hashtags and off-the-shelf taggers. Project page:https://github.com/TencentARC/TagGPT.

TagGPT: Large Language Models are Zero-shot Multimodal Taggers