Dialogue State Tracking On Cosql
评估指标
interaction match accuracy
question match accuracy
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | |||
|---|---|---|---|---|
| RASAT+PICARD | 26.5 | 55.7 | RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL | |
| HIE-SQL + GraPPa | 24.6 | 53.9 | HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing | - |
| T5-3B + PICARD | 23.7 | 54.6 | PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models | |
| RAT-SQL + SCoRe | 21.2 | 51.6 | SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing | - |
| R²SQL + BERT | 17.0 | 46.8 | Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing | |
| Edit-SQL+BERT | 13.7 | 40.8 | Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions | |
| GAZP+BERT | 12.8 | 39.7 | Grounded Adaptation for Zero-shot Executable Semantic Parsing | |
| CD-Seq2seq | 2.6 | 13.9 | CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases | |
| SyntaxSQL-con | 2.2 | 14.1 | CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases |
0 of 9 row(s) selected.