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

The rapid proliferation of e-commerce platforms accentuates the need foradvanced search and retrieval systems to foster a superior user experience.Central to this endeavor is the precise extraction of product attributes fromcustomer queries, enabling refined search, comparison, and other cruciale-commerce functionalities. Unlike traditional Named Entity Recognition (NER)tasks, e-commerce queries present a unique challenge owing to the intrinsicdecorative relationship between product types and attributes. In this study, wepropose a pioneering framework that integrates BERT for classification, aConditional Random Fields (CRFs) layer for attribute value extraction, andLarge Language Models (LLMs) for data annotation, significantly advancingattribute recognition from customer inquiries. Our approach capitalizes on therobust representation learning of BERT, synergized with the sequence decodingprowess of CRFs, to adeptly identify and extract attribute values. We introducea novel decorative relation correction mechanism to further refine theextraction process based on the nuanced relationships between product types andattributes inherent in e-commerce data. Employing LLMs, we annotate additionaldata to expand the model's grasp and coverage of diverse attributes. Ourmethodology is rigorously validated on various datasets, including Walmart,BestBuy's e-commerce NER dataset, and the CoNLL dataset, demonstratingsubstantial improvements in attribute recognition performance. Particularly,the model showcased promising results during a two-month deployment inWalmart's Sponsor Product Search, underscoring its practical utility andeffectiveness.

Enhanced E-Commerce Attribute Extraction: Innovating with Decorative Relation Correction and LLAMA 2.0-Based Annotation