DeepAI AI Chat
Log In Sign Up

Learning to Synthesize Data for Semantic Parsing

04/12/2021
by   Bailin Wang, et al.
Facebook
Salesforce
0

Synthesizing data for semantic parsing has gained increasing attention recently. However, most methods require handcrafted (high-precision) rules in their generative process, hindering the exploration of diverse unseen data. In this work, we propose a generative model which features a (non-neural) PCFG that models the composition of programs (e.g., SQL), and a BART-based translation model that maps a program to an utterance. Due to the simplicity of PCFG and pre-trained BART, our generative model can be efficiently learned from existing data at hand. Moreover, explicitly modeling compositions using PCFG leads to a better exploration of unseen programs, thus generate more diverse data. We evaluate our method in both in-domain and out-of-domain settings of text-to-SQL parsing on the standard benchmarks of GeoQuery and Spider, respectively. Our empirical results show that the synthesized data generated from our model can substantially help a semantic parser achieve better compositional and domain generalization.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/09/2018

Robust Text-to-SQL Generation with Execution-Guided Decoding

We consider the problem of neural semantic parsing, which translates nat...
12/04/2021

Hierarchical Neural Data Synthesis for Semantic Parsing

Semantic parsing datasets are expensive to collect. Moreover, even the q...
10/23/2022

Towards Generalizable and Robust Text-to-SQL Parsing

Text-to-SQL parsing tackles the problem of mapping natural language ques...
12/17/2022

Importance of Synthesizing High-quality Data for Text-to-SQL Parsing

Recently, there has been increasing interest in synthesizing data to imp...
06/04/2021

Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL

Recently, Text-to-SQL for multi-turn dialogue has attracted great intere...
09/12/2019

Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning

Neural semantic parsing has achieved impressive results in recent years,...
01/26/2023

Neural-Symbolic Inference for Robust Autoregressive Graph Parsing via Compositional Uncertainty Quantification

Pre-trained seq2seq models excel at graph semantic parsing with rich ann...