Research map / Label-efficient and robust learning / Recognition and long-tail
A Multi-Task Learning Approach for Improving Product Title Compression with User Search Log Data
Jingang Wang, Junfeng Tian, Long Qiu, Sheng Li, Jun Lang, Luo Si, Man Lan
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 attention-distribution agreement between title compression and query generation (ablation) | Multi-task title compression · Women's Clothes test set | ROUGE-1: 65.92 -> 70.89 | Improved |
| add attention-distribution agreement between title compression and query generation (ablation) | Multi-task title compression · Women's Clothes test set | ROUGE-2: 52.94 -> 56.80 | Improved |
| add attention-distribution agreement between title compression and query generation (ablation) | Multi-task title compression · Women's Clothes test set | ROUGE-L: 65.20 -> 69.61 | Improved |
| add query-generation task and shared encoder without attention agreement (ablation) | Ptr-Net · Women's Clothes test set | ROUGE-1: 69.03 -> 65.92 | Hurt |
| add query-generation task and shared encoder without attention agreement (ablation) | Ptr-Net · Women's Clothes test set | ROUGE-2: 55.30 -> 52.94 | Hurt |
| add query-generation task and shared encoder without attention agreement (ablation) | Ptr-Net · Women's Clothes test set | ROUGE-L: 67.98 -> 65.20 | Hurt |
| replace ILP compression with Agree-MTL | Product title compression · Online A/B test, Women's Clothes | CTR: +2.58% | Improved |
| replace ILP compression with Agree-MTL | Product title compression · Online A/B test, Women's Clothes | CVR: +1.32% | Improved |
| replace ILP with Agree-MTL | Product title compression · Women's Clothes manual evaluation | Readability: 4.63 -> 4.80 | Improved |
| replace ILP with Agree-MTL | Product title compression · Women's Clothes manual evaluation | Informativeness: 3.90 -> 4.66 | Improved |
Closest papers by meaning
- Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders (ICLR 2024 · similarity 0.81)
- Leveraging Attention to Effectively Compress Prompts for Long-Context LLMs (AAAI 2025 · similarity 0.81)
- EcomGPT: Instruction-Tuning Large Language Models with Chain-of-Task Tasks for E-commerce (AAAI 2024 · similarity 0.81)
- RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation (ICLR 2024 · similarity 0.81)
- UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence (NeurIPS 2026 · similarity 0.81)
- Some Like It Small: Czech Semantic Embedding Models for Industry Applications (AAAI 2024 · similarity 0.80)
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.
