Controllable Semantic Parsing via Retrieval Augmentation

TL;DR

This paper introduces CASPER, a controllable semantic parser that uses exemplar retrieval to adapt to new domains or behaviors without retraining, enhancing flexibility and efficiency in semantic parsing tasks.

Contribution

The paper presents a novel retrieval-augmented approach for semantic parsing that allows behavior control and domain adaptation without additional training.

Findings

Achieves state-of-the-art results on MTOP dataset.

Can adapt to new domains and schemas without retraining.

Demonstrates flexible control over parsing behavior.

Abstract

In practical applications of semantic parsing, we often want to rapidly change the behavior of the parser, such as enabling it to handle queries in a new domain, or changing its predictions on certain targeted queries. While we can introduce new training examples exhibiting the target behavior, a mechanism for enacting such behavior changes without expensive model re-training would be preferable. To this end, we propose ControllAble Semantic Parser via Exemplar Retrieval (CASPER). Given an input query, the parser retrieves related exemplars from a retrieval index, augments them to the query, and then applies a generative seq2seq model to produce an output parse. The exemplars act as a control mechanism over the generic generative model: by manipulating the retrieval index or how the augmented query is constructed, we can manipulate the behavior of the parser. On the MTOP dataset, in addition to achieving state-of-the-art on the standard setup, we show that CASPER can parse queries in a new domain, adapt the prediction toward the specified patterns, or adapt to new semantic schemas without having to further re-train the model.