Zero-Shot Semantic Parsing for Instructions

TL;DR

This paper introduces a zero-shot semantic parsing approach that generalizes instruction understanding to unseen domains using a new dataset and an enhanced training algorithm integrated into a floating parser.

Contribution

It presents a novel zero-shot training algorithm and dataset for semantic parsing across unseen domains, improving parser adaptability and performance.

Findings

Significant performance improvements in zero-shot domain adaptation.

A new dataset with 1,390 examples across 7 domains.

Enhanced parser with features and candidate filtering.

Abstract

We consider a zero-shot semantic parsing task: parsing instructions into compositional logical forms, in domains that were not seen during training. We present a new dataset with 1,390 examples from 7 application domains (e.g. a calendar or a file manager), each example consisting of a triplet: (a) the application's initial state, (b) an instruction, to be carried out in the context of that state, and (c) the state of the application after carrying out the instruction. We introduce a new training algorithm that aims to train a semantic parser on examples from a set of source domains, so that it can effectively parse instructions from an unknown target domain. We integrate our algorithm into the floating parser of Pasupat and Liang (2015), and further augment the parser with features and a logical form candidate filtering logic, to support zero-shot adaptation. Our experiments with various zero-shot adaptation setups demonstrate substantial performance gains over a non-adapted parser.