RECPARSER: A Recursive Semantic Parsing Framework for Text-to-SQL Task
Authors: Yu Zeng, Yan Gao, Jiaqi Guo, Bei Chen, Qian Liu, Jian-Guang Lou, Fei Teng, Dongmei Zhang
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on the Spider dataset show that our approach is more effective compared to the previous works at predicting the nested SQL queries. In addition, we achieve an overall accuracy that is comparable with state-of-the-art approaches. |
| Researcher Affiliation | Collaboration | 1Southwest Jiaotong University, Chengdu, China 2Microsoft Research Asia, Beijing, China 3Xi an Jiaotong University, Xi an, China 4Beihang University, Beijing, China |
| Pseudocode | No | The paper describes the system architecture and components in prose and diagrams, but does not provide structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing the source code for the methodology or provide a link to a code repository. |
| Open Datasets | Yes | Dataset. We conduct our experiments on Spider [Yu et al., 2018b], a large-scale, human-annotated and crossdomain Text-to-SQL benchmark, which contains 7,000/1,034 question-SQL query pairs in train and development set. |
| Dataset Splits | Yes | Dataset. We conduct our experiments on Spider [Yu et al., 2018b], a large-scale, human-annotated and crossdomain Text-to-SQL benchmark, which contains 7,000/1,034 question-SQL query pairs in train and development set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running experiments, such as GPU or CPU models. |
| Software Dependencies | No | The paper mentions software like PyTorch, Adam, and Glove, but does not specify their version numbers for reproducibility. |
| Experiment Setup | Yes | The dropout rate is 0.2. We use Adam with 1e-3 learning rate for optimization. Batch size is 64. Word embeddings are initialized with Glove. The dimensions of word embedding, type embedding and hidden vectors are set to 300. λAGG, λOP , λNES, λIUE, λLIMIT , λdiv in Equation 7 are set as 1, 1, 1, 0.1, 0.1, and 0.2 respectively. |