CLSep 19, 2018

Unsupervised cross-lingual matching of product classifications

arXiv:1809.07234v12 citations
Originality Synthesis-oriented
AI Analysis

This work addresses a domain-specific problem in multilingual product classification matching, but it appears incremental as it builds on existing unsupervised methods.

The paper tackled the problem of unsupervised cross-lingual matching of product classifications by applying unsupervised cross-lingual embeddings mapping, and it investigated limitations and suggested additional techniques like hierarchical information and translations for alignment.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes