Grounded Adaptation for Zero-shot Executable Semantic Parsing

By Victor Zhong, Michael Lewis, Sida I. Wang, Luke S. Zettlemoyer. 2020

115 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Break-It-Fix-It: Unsupervised Learning for Program Repair (2021, methodology): “This is commonly used in structured generation problems such as semantic parsing, program synthesis and molecule generation (Liang et al., 2013; Berant et al., 2013; Guu et al., 2017; Min et al., 2019; Zhong et al., 2020; Yang et al., 2020).”
TAPEX: Table Pre-training via Learning a Neural SQL Executor (2021, methodology): “In this experiment, we follow Zhong et al. (2020a) to train a SQL-to-NL model and employ the model to translate SQL queries from the pre-training corpus into NL sentences.”
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing (2020, background): “Pre-training vs. training data augmentation Many recent work (Zhang et al., 2019b; Herzig et al., 2020b; Campagna et al., 2020; Zhong et al., 2020) in semantic parsing and dialog state tracking show that training models on a combination of the extra synthetic data and original training data does…”
SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models (2022, methodology): “Zhong et al. (2020) explored zero-shot semantic parsing via generation-model-based data augmentation.”