Research map / Label-efficient and robust learning / Recognition and long-tail
Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce
Juntao Li, Chang Liu, Jian Wang, Lidong Bing, Hongsong Li, Xiaozhong Liu, Dongyan Zhao, Rui Yan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add context-dependent cross-lingual mapping on BERT | CLMN · CLIR-EC | R10@1: 83.8 -> 86.8 | Improved |
| Use BERT instead of domain-specific word embeddings (ablation) | CLMN · CLIR-EC | R10@1: 83.5 -> 86.8 | Improved |
| Add cross-lingual alignment (ablation) | CLMN with BERT · CLIR-EC | R10@1: 80.7 -> 86.8 | Improved |
| Add cross-lingual alignment (ablation) | CLMN with word embeddings · CLIR-EC | R10@1: 78.3 -> 83.5 | Improved |
| Score in English bilingual space rather than Chinese bilingual space (ablation) | CLMN with BERT · CLIR-EC | R10@1: 84.6 -> 85.5 | Improved |
| Score in English bilingual space rather than Chinese bilingual space (ablation) | CLMN with word embeddings · CLIR-EC | R10@1: 81.5 -> 81.8 | Improved |
| Add attention-based matching instead of the SMN matching model | Translation-based CLIR · CLIR-EC | R10@1: 73.6 -> 78.5 | Improved |
| Use direct cross-lingual retrieval instead of translation-based retrieval | CLIR-EC retrieval · CLIR-EC | R10@1: 79.8 -> 86.8 | Improved |
Closest papers by meaning
- CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer (AAAI 2024 · similarity 0.85)
- MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query (NeurIPS 2025 · similarity 0.85)
- eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data (ICML 2024 · similarity 0.83)
- Soft Token Alignment for Cross-Lingual Reasoning (NeurIPS 2026 · similarity 0.83)
- EcomGPT: Instruction-Tuning Large Language Models with Chain-of-Task Tasks for E-commerce (AAAI 2024 · similarity 0.83)
- Multi-Domain Deep Learning from a Multi-View Perspective for Cross-Border E-commerce Search (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
