Grounded Adaptation for Zero-shot Executable Semantic Parsing
release_hi23ffdeavam5hyciex6c7oidm
by
Victor Zhong, Mike Lewis, Sida I. Wang, Luke Zettlemoyer
2021
Abstract
We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing
(GAZP) to adapt an existing semantic parser to new environments (e.g. new
database schemas). GAZP combines a forward semantic parser with a backward
utterance generator to synthesize data (e.g. utterances and SQL queries) in the
new environment, then selects cycle-consistent examples to adapt the parser.
Unlike data-augmentation, which typically synthesizes unverified examples in
the training environment, GAZP synthesizes examples in the new environment
whose input-output consistency are verified. On the Spider, Sparc, and CoSQL
zero-shot semantic parsing tasks, GAZP improves logical form and execution
accuracy of the baseline parser. Our analyses show that GAZP outperforms
data-augmentation in the training environment, performance increases with the
amount of GAZP-synthesized data, and cycle-consistency is central to successful
adaptation.
In text/plain
format
Archived Content
There are no accessible files associated with this release. You could check other releases for this work for an accessible version.
Know of a fulltext copy of on the public web? Submit a URL and we will archive it
2009.07396v3
access all versions, variants, and formats of this works (eg, pre-prints)