Mention Extraction and Linking for SQL Query Generation

Jianqiang Ma, Zeyu Yan, Shuai Pang, Yang Zhang, Jianping Shen

Semantics: Sentence-level Semantics, Textual Inference and Other areas Short Paper

Gather-4F: Nov 18, Gather-4F: Nov 18 (02:00-04:00 UTC) [Join Gather Meeting]

You can open the pre-recorded video in a separate window.

Abstract: On the WikiSQL benchmark, state-of-the-art text-to-SQL systems typically take a slot- filling approach by building several dedicated models for each type of slots. Such modularized systems are not only complex but also of limited capacity for capturing inter-dependencies among SQL clauses. To solve these problems, this paper proposes a novel extraction-linking approach, where a unified extractor recognizes all types of slot mentions appearing in the question sentence before a linker maps the recognized columns to the table schema to generate executable SQL queries. Trained with automatically generated annotations, the proposed method achieves the first place on the WikiSQL benchmark.
NOTE: Video may display a random order of authors. Correct author list is at the top of this page.

Connected Papers in EMNLP2020

Similar Papers

Efficient One-Pass End-to-End Entity Linking for Questions
Belinda Z. Li, Sewon Min, Srinivasan Iyer, Yashar Mehdad, Wen-tau Yih,
DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset
Lijie Wang, Ao Zhang, Kun Wu, Ke Sun, Zhenghua Li, Hua Wu, Min Zhang, Haifeng Wang,
Entity Linking in 100 Languages
Jan A. Botha, Zifei Shan, Daniel Gillick,
ENT-DESC: Entity Description Generation by Exploring Knowledge Graph
Liying Cheng, Dekun Wu, Lidong Bing, Yan Zhang, Zhanming Jie, Wei Lu, Luo Si,