TY - JOUR
AU - 
AB - RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers y z Bailin Wang Richard Shin University of Edinburgh UC Berkeley bailin.wang@ed.ac.uk ricshin@cs.berkeley.edu Xiaodong Liu Oleksandr Polozov Matthew Richardson Microsoft Research, Redmond {xiaodl,polozov,mattri}@microsoft.com Abstract 2018), new tasks such as WikiSQL (Zhong et al., 2017) and Spider (Yu et al., 2018b) pose the real- When translating natural language questions life challenge of generalization to unseen database into SQL queries to answer questions from a schemas. Every query is conditioned on a multi- database, contemporary semantic parsing mod- table database schema, and the databases do not els struggle to generalize to unseen database overlap between the train and test sets. schemas. The generalization challenge lies in (a) encoding the database relations in an Schema generalization is challenging for three accessible way for the semantic parser, and interconnected reasons. First, any text-to-SQL pars- (b) modeling alignment between database ing model must encode the schema into representa- columns and their mentions in a given query. tions suitable for decoding a SQL query that might We present a unified framework, based on the involve the given columns or tables. Second, these relation-aware self-attention mechanism, to representations should encode all the information address schema encoding, schema 
TI - RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers
JF - Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
DO - 10.18653/v1/2020.acl-main.677
DA - 2020-01-01
UR - https://www.deepdyve.com/lp/unpaywall/rat-sql-relation-aware-schema-encoding-and-linking-for-text-to-sql-t0eKWOdXQ9
DP - DeepDyve
ER -