Published November 16, 2018
| Version v1
Conference paper
Open
Unsupervised Cross-lingual Matching of Product Classifications
Creators
- 1. Russian Presidential Academy of National Economy and Public Administration
Description
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
Files
CUsersRussiaFRUCTprocessing3.Zenodo_DOI..2.FRUCT_PublicationFRUCT23papersGor.pdf
Files
(706.9 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:3e6c9a985cabe88d7909608f5fe92de9
|
706.9 kB | Preview Download |