Zero-Shot Semantic Parsing for Instructions

11/20/2019
by   Ofer Givoli, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/21/2018

Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing

Building a semantic parser quickly in a new domain is a fundamental chal...
09/16/2020

Grounded Adaptation for Zero-shot Executable Semantic Parsing

We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing...
08/27/2018

Zero-shot Transfer Learning for Semantic Parsing

While neural networks have shown impressive performance on large dataset...
04/17/2019

CraftAssist Instruction Parsing: Semantic Parsing for a Minecraft Assistant

We propose a large scale semantic parsing dataset focused on instruction...
10/15/2021

On The Ingredients of an Effective Zero-shot Semantic Parser

Semantic parsers map natural language utterances into meaning representa...
01/13/2020

Exploiting Language Instructions for Interpretable and Compositional Reinforcement Learning

In this work, we present an alternative approach to making an agent comp...
12/07/2021

Multinational Address Parsing: A Zero-Shot Evaluation

Address parsing consists of identifying the segments that make up an add...

Code Repositories

TechnionNLI

This repository contains the dataset and code for the ACL 2019 paper "Zero-Shot Semantic Parsing for Instructions" by Ofer Givoli and Roi Reichart.


view repo