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

Product attribute value extraction is an important task in e-Commerce whichcan help several downstream applications such as product search andrecommendation. Most previous models handle this task using sequence labelingor question answering method which rely on the sequential position informationof values in the product text and are vulnerable to data discrepancy betweentraining and testing. This limits their generalization ability to real-worldscenario in which each product can have multiple descriptions across variousshopping platforms with different composition of text and style. They also havelimited zero-shot ability to new values. In this paper, we propose a multi-tasklearning model with value generation/classification and attribute predictioncalled JPAVE to predict values without the necessity of position information ofvalues in the text. Furthermore, the copy mechanism in value generator and thevalue attention module in value classifier help our model address the datadiscrepancy issue by only focusing on the relevant part of input text andignoring other information which causes the discrepancy issue such as sentencestructure in the text. Besides, two variants of our model are designed foropen-world and closed-world scenarios. In addition, copy mechanism introducedin the first variant based on value generation can improve its zero-shotability for identifying unseen values. Experimental results on a public datasetdemonstrate the superiority of our model compared with strong baselines and itsgeneralization ability of predicting new values.

JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction