Unsupervised cross-lingual matching of product classifications

2018/09/19 by Denis Gordeev, Gordeev, Denis, Alexey Rey +3
Computer Science · #68T50 #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text and Document Classification Technologies #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1809.07234

openalex publication_date 2018/09/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Learning Multilingual Word Embeddings in Latent Metric Space: A\n Geometric Approach

Related

• Unsupervised Hyperalignment for Multilingual Word Embeddings
• Product-oriented Machine Translation with Cross-modal Cross-lingual Pre-training
• A Semantic Alignment System for Multilingual Query-Product Retrieval
• Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce
• A Simple Approach to Learning Unsupervised Multilingual Embeddings