Don't Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding

10/08/2020
by   Qile Zhu, et al.
7

Semantic parsing is one of the key components of natural language understanding systems. A successful parse transforms an input utterance to an action that is easily understood by the system. Many algorithms have been proposed to solve this problem, from conventional rulebased or statistical slot-filling systems to shiftreduce based neural parsers. For complex parsing tasks, the state-of-the-art method is based on autoregressive sequence to sequence models to generate the parse directly. This model is slow at inference time, generating parses in O(n) decoding steps (n is the length of the target sequence). In addition, we demonstrate that this method performs poorly in zero-shot cross-lingual transfer learning settings. In this paper, we propose a non-autoregressive parser which is based on the insertion transformer to overcome these two issues. Our approach 1) speeds up decoding by 3x while outperforming the autoregressive model and 2) significantly improves cross-lingual transfer in the low-resource setting by 37 autoregressive baseline. We test our approach on three well-known monolingual datasets: ATIS, SNIPS and TOP. For cross lingual semantic parsing, we use the MultiATIS++ and the multilingual TOP datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/06/2017

Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages

In cross-lingual dependency annotation projection, information is often ...
research
04/15/2021

Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing

An effective recipe for building seq2seq, non-autoregressive, task-orien...
research
10/07/2019

MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging

This paper describes our recursive system for SemEval-2019 Task 1: Cros...
research
06/07/2021

X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing

Task-oriented compositional semantic parsing (TCSP) handles complex nest...
research
10/23/2020

SmBoP: Semi-autoregressive Bottom-up Semantic Parsing

The de-facto standard decoding method for semantic parsing in recent yea...
research
05/29/2019

A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models

Undirected neural sequence models such as BERT have received renewed int...
research
02/02/2022

Retrieve-and-Fill for Scenario-based Task-Oriented Semantic Parsing

Task-oriented semantic parsing models have achieved strong results in re...

Please sign up or login with your details

Forgot password? Click here to reset