Unsupervised cross-lingual matching of product classifications

09/19/2018

∙

by   Denis Gordeev, et al.

∙

0

∙

share

Unsupervised cross-lingual embeddings mapping has provided a unique tool for completely unsupervised translation even for languages with different scripts. In this work we use this method for the task of unsupervised cross-lingual matching of product classifications. Our work also investigates limitations of unsupervised vector alignment and we also suggest two other techniques for aligning product classifications based on their descriptions: using hierarchical information and translations.