Research map / Large language models / Language, safety and interpretability
Dynamic Hybrid Relation Exploration Network for Cross-Domain Context-Dependent Semantic Parsing
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 |
|---|---|---|---|
| combine implicit- and explicit-relation exploration rather than using either alone (ablation) | Dynamic Hybrid Relation Exploration Network · SParC dev | question match: 48.0 / 48.3 -> 51.1 | Helped |
| add schedule-based memory decay to relation exploration (ablation) | Dynamic Hybrid Relation Exploration Network · CoSQL dev | interaction match: 14.0 -> 16.1 | Helped |
| add gate-based memory decay to relation exploration (ablation) | Dynamic Hybrid Relation Exploration Network · CoSQL dev | interaction match: 14.0 -> 15.4 | Helped |
| add task-related hidden representations to the reranker (ablation) | Dynamic Hybrid Relation Exploration Network · CoSQL dev | interaction match: 18.6 -> 19.5 | Helped |
| add the dynamic hybrid graph framework and reranking to the EditSQL+BERT baseline | Text-to-SQL parsing · SParC test | question match: 47.9 -> 55.8 | Helped |
| add the dynamic hybrid graph framework and reranking to the EditSQL+BERT baseline | Text-to-SQL parsing · CoSQL test | interaction match: 13.7 -> 17.0 | Helped |
Closest papers by meaning
- Filling Memory Gaps: Enhancing Continual Semantic Parsing via SQL Syntax Variance-Guided LLMs Without Real Data Replay (AAAI 2025 · similarity 0.86)
- Provence: efficient and robust context pruning for retrieval-augmented generation (ICLR 2025 · similarity 0.86)
- Reasoning of Large Language Models over Knowledge Graphs with Super-Relations (ICLR 2025 · similarity 0.86)
- From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs (ICLR 2025 · similarity 0.86)
- L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling (NeurIPS 2025 · similarity 0.86)
- AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries (NeurIPS 2024 · similarity 0.85)
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.