Unsupervised Cross-lingual Matching of Product Classifications

Denis Gordeev, Alexey Rey, Dmitry Shagarov
2018 Zenodo  
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
doi:10.5281/zenodo.4553685 fatcat:odgsdgntxbcgvdy6jkgiel3264