SParC: Cross-Domain Semantic Parsing in Context
| Autor: | Emily Ji, Rui Zhang, Heyang Er, Michihiro Yasunaga, Bo Pang, Suyi Li, Dragomir R. Radev, Caiming Xiong, Irene Li, Yi Chern Tan, David Proctor, Richard Socher, Sungrok Shim, Vincent Zhang, Xi Victoria Lin, Shreya Dixit, Jonathan Kraft, Tao Chen, Tao Yu |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
SQL Computer Science - Computation and Language Parsing Computer Science - Artificial Intelligence Computer science Generalization business.industry Context (language use) 02 engineering and technology computer.software_genre Domain (software engineering) 03 medical and health sciences Artificial Intelligence (cs.AI) 0302 clinical medicine 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Computation and Language (cs.CL) computer Natural language processing computer.programming_language |
| Zdroj: | ACL (1) |
| DOI: | 10.18653/v1/p19-1443 |
| Popis: | We present SParC, a dataset for cross-domainSemanticParsing inContext that consists of 4,298 coherent question sequences (12k+ individual questions annotated with SQL queries). It is obtained from controlled user interactions with 200 complex databases over 138 domains. We provide an in-depth analysis of SParC and show that it introduces new challenges compared to existing datasets. SParC demonstrates complex contextual dependencies, (2) has greater semantic diversity, and (3) requires generalization to unseen domains due to its cross-domain nature and the unseen databases at test time. We experiment with two state-of-the-art text-to-SQL models adapted to the context-dependent, cross-domain setup. The best model obtains an exact match accuracy of 20.2% over all questions and less than10% over all interaction sequences, indicating that the cross-domain setting and the con-textual phenomena of the dataset present significant challenges for future research. The dataset, baselines, and leaderboard are released at https://yale-lily.github.io/sparc. Accepted to ACL 2019, long paper |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|