SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL
Dec 6, 2021
Speakers
Ruichu Cai
Speaker · 0 followers
Jinjie Yuan
Speaker · 0 followers
Zhifeng Hao
Speaker · 0 followers
About
The Text-to-SQL task, aiming to translate the natural language of the questions into SQL queries, has drawn much attention recently. One of the most challenging problems of Text-to-SQL is how to generalize the trained model to the unseen databases schema, also known as the cross-domain Text-to-SQL task. The key lies in the generalizability of (i) the encoding method to model the question and the database schema and (ii) the question-schema linking method to learning the mapping between the words in the question and the tables/columns in the database schema. Focusing on the above two key issues, we propose a Structure-Aware Dual Graph Aggregation Network (SADGA) for the cross-domain Text-to-SQL task. In SADGA, we adopt the graph structure to provide a unified encoding model for both the natural language question and database schema. Based on the proposed unified modeling, we further devise a structure-aware aggregation method to learn the mapping between the question-graph and schema-graph. The structure-aware aggregation method is featured with Global Graph Linking, Local Graph Linking and Dual-Graph Aggregation Mechanism. We not only study the performance of our proposal empirically but also achieve 3rd place on the challenging Text-to-SQL benchmark Spider.The Text-to-SQL task, aiming to translate the natural language of the questions into SQL queries, has drawn much attention recently. One of the most challenging problems of Text-to-SQL is how to generalize the trained model to the unseen databases schema, also known as the cross-domain Text-to-SQL task. The key lies in the generalizability of (i) the encoding method to model the question and the database schema and (ii) the question-schema linking method to learning the mapping between the words…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Unlabeled Principal Component Analysis
Watch later
Yunzhen Yao, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Electromagnetic Counterpart Identification of Gravitational-wave candidates using deep-learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Identifiable Generative models for Missing Not at Random Data Imputation
Watch later
Chao Ma, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Selective Sampling for Online Best-arm Identification
Watch later
Zhihan Xiong, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Multi-party referential communication in complex strategic games
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Model Selection for Bayesian Autoencoders
Watch later
Ba-Hien Tran, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%