Unsupervised cross-lingual matching of product classifications [article]

Denis Gordeev, Alexey Rey, Dmitry Shagarov
2018 arXiv   pre-print
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.
arXiv:1809.07234v1 fatcat:damki7den5dwzgk5wnvzkzsmlm