DialSQL: Dialogue Based Structured Query Generation
| Autor: | Xifeng Yan, Semih Yavuz, Yu Su, Izzeddin Gur |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
SQL
Information retrieval Parsing SIMPLE (military communications protocol) business.industry Computer science Deep learning 02 engineering and technology computer.software_genre 020204 information systems 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business computer Natural language computer.programming_language |
| Zdroj: | ACL (1) |
| DOI: | 10.18653/v1/p18-1124 |
| Popis: | The recent advance in deep learning and semantic parsing has significantly improved the translation accuracy of natural language questions to structured queries. However, further improvement of the existing approaches turns out to be quite challenging. Rather than solely relying on algorithmic innovations, in this work, we introduce DialSQL, a dialogue-based structured query generation framework that leverages human intelligence to boost the performance of existing algorithms via user interaction. DialSQL is capable of identifying potential errors in a generated SQL query and asking users for validation via simple multi-choice questions. User feedback is then leveraged to revise the query. We design a generic simulator to bootstrap synthetic training dialogues and evaluate the performance of DialSQL on the WikiSQL dataset. Using SQLNet as a black box query generation tool, DialSQL improves its performance from 61.3% to 69.0% using only 2.4 validation questions per dialogue. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|