Relation Aware Semi-autoregressive Semantic Parsing for NL2SQL
This work addresses a domain-specific challenge in NL2SQL for practical Internet applications, but it appears incremental as it builds on existing methods like ELECTRA and transformers.
The paper tackles the problem of learning better word representations in NL2SQL by proposing a relation-aware semi-autoregressive framework, which improves performance on this task as shown in empirical results.
Natural language to SQL (NL2SQL) aims to parse a natural language with a given database into a SQL query, which widely appears in practical Internet applications. Jointly encode database schema and question utterance is a difficult but important task in NL2SQL. One solution is to treat the input as a heterogeneous graph. However, it failed to learn good word representation in question utterance. Learning better word representation is important for constructing a well-designed NL2SQL system. To solve the challenging task, we present a Relation aware Semi-autogressive Semantic Parsing (\MODN) ~framework, which is more adaptable for NL2SQL. It first learns relation embedding over the schema entities and question words with predefined schema relations with ELECTRA and relation aware transformer layer as backbone. Then we decode the query SQL with a semi-autoregressive parser and predefined SQL syntax. From empirical results and case study, our model shows its effectiveness in learning better word representation in NL2SQL.