Caiming Xiong, Bailin Wang, Wenpeng Yin, Victoria Lin, Xi
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Synthesizing data for semantic parsing has gained increasing attention recently. However, most methods require handcrafted (highprecision) 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-ofdomain settings of text-to-SQL parsing on the standard benchmarks of GEOQUERY and SPI-DER, 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.05827")
get_code_for_paper("2104.05827")
have("2104.05827")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.05827.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.05827)
Connect an agent — have() is free.