Dialogue State Tracking On Cosql
Metrics
interaction match accuracy
question match accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | interaction match accuracy | question match accuracy |
|---|---|---|
| grounded-adaptation-for-zero-shot-executable | 12.8 | 39.7 |
| cosql-a-conversational-text-to-sql-challenge | 2.2 | 14.1 |
| rasat-integrating-relational-structures-into | 26.5 | 55.7 |
| hie-sql-history-information-enhanced-network | 24.6 | 53.9 |
| cosql-a-conversational-text-to-sql-challenge | 2.6 | 13.9 |
| dynamic-hybrid-relation-network-for-cross | 17.0 | 46.8 |
| score-pre-training-for-context-representation | 21.2 | 51.6 |
| editing-based-sql-query-generation-for-cross | 13.7 | 40.8 |
| picard-parsing-incrementally-for-constrained | 23.7 | 54.6 |