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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Existing pre-trained language models (PLMs) have demonstrated theeffectiveness of self-supervised learning for a broad range of natural languageprocessing (NLP) tasks. However, most of them are not explicitly aware ofdomain-specific knowledge, which is essential for downstream tasks in manydomains, such as tasks in e-commerce scenarios. In this paper, we proposeK-PLUG, a knowledge-injected pre-trained language model based on theencoder-decoder transformer that can be transferred to both natural languageunderstanding and generation tasks. We verify our method in a diverse range ofe-commerce scenarios that require domain-specific knowledge. Specifically, wepropose five knowledge-aware self-supervised pre-training objectives toformulate the learning of domain-specific knowledge, including e-commercedomain-specific knowledge-bases, aspects of product entities, categories ofproduct entities, and unique selling propositions of product entities. K-PLUGachieves new state-of-the-art results on a suite of domain-specific NLP tasks,including product knowledge base completion, abstractive product summarization,and multi-turn dialogue, significantly outperforms baselines across the board,which demonstrates that the proposed method effectively learns a diverse set ofdomain-specific knowledge for both language understanding and generation tasks.

K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce