Research map / Vision-language and multimodal / Visual question answering
Improving Recommendation of Tail Tags for Questions in Community Question Answering
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 learned question and tag similarity with feature fusion instead of tf x idf heuristic (ablation) | tag recommendation model · Quora | P@1: 0.523 -> 0.553 | Helped |
| add learned question and tag similarity with feature fusion instead of tf x idf heuristic (ablation) | tag recommendation model · Quora | Pt@1: 0.214 -> 0.165 | Hurt |
| add learned question and tag similarity instead of tf x idf heuristic (ablation) | tag recommendation model · Zhihu | P@1: 0.511 -> 0.577 | Helped |
| fuse multiple features instead of one feature (ablation) | tag recommendation model · Quora | Pt@1: 0.161 -> 0.165 | Helped |
| fuse multiple features instead of one feature (ablation) | tag recommendation model · Zhihu | Pt@1: 0.171 -> 0.176 | Helped |
| add question similarity to tag-similarity-only variant (ablation) | tag recommendation model · Quora | P@1: 0.535 -> 0.553 | Helped |
| add tag similarity to question-similarity-only variant (ablation) | tag recommendation model · Quora | Pt@1: 0.161 -> 0.165 | Helped |
| add tag similarity to question-similarity-only variant (ablation) | tag recommendation model · Quora | P@1: 0.550 -> 0.553 | No clear effect |
| use proposed model instead of HGM | tag recommendation model · Zhihu | P@1: 0.427 -> 0.577 | Helped |
| use proposed model instead of HGM | tag recommendation model · Quora | Pt@5: 0.097 -> 0.092 | Mixed |
Closest papers by meaning
- Beyond Static: Related Questions Retrieval Through Conversations in Community Question Answering (AAAI 2026 · similarity 0.88)
- An Integral Tag Recommendation Model for Textual Content (AAAI 2019 · similarity 0.84)
- Knowledge Tagging with Large Language Model Based Multi-Agent System (AAAI 2025 · similarity 0.81)
- Tail-STEAK: Improve Friend Recommendation for Tail Users via Self-Training Enhanced Knowledge Distillation (AAAI 2024 · similarity 0.80)
- C-SEO Bench: Does Conversational SEO Work? (NeurIPS 2025 · similarity 0.80)
- Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge (NeurIPS 2026 · 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.