On robustness of neural semantic parsers

Huang, Shuo, Li, Zhuang, Qu, Lizhen and Pan, Lei 2021, On robustness of neural semantic parsers, in EACL 2021 : Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, Stroudsburg, Pa., pp. 3333-3342.

Attached Files
Name Description MIMEType Size Downloads

Title On robustness of neural semantic parsers
Author(s) Huang, Shuo
Li, Zhuang
Qu, Lizhen
Pan, LeiORCID iD for Pan, Lei orcid.org/0000-0002-4691-8330
Conference name Association for Computational Linguistics. Conference (16th : 2021 : Online)
Conference location Online
Conference dates 2021/04/19 - 2021/04/23
Title of proceedings EACL 2021 : Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics
Editor(s) Merlo, P
Tiedemann, J
Tsarfaty, R
Publication date 2021
Series Association for Computational Linguistics Conference
Start page 3333
End page 3342
Total pages 10
Publisher Association for Computational Linguistics
Place of publication Stroudsburg, Pa.
Keyword(s) natural language (NL)
parsing maps
logical forms (LFs)
Semantic parsers
Summary Semantic parsing maps natural language (NL) utterances into logical forms (LFs), which underpins many advanced NLP problems. Semantic parsers gain performance boosts with deep neural networks, but inherit vulnerabilities against adversarial examples. In this paper, we provide the first empirical study on the robustness of semantic parsers in the presence of adversarial attacks. Formally, adversaries of semantic parsing are considered to be the perturbed utterance-LF pairs, whose utterances have exactly the same meanings as the original ones. A scalable methodology is proposed to construct robustness test sets based on existing benchmark corpora. Our results answered five research questions in measuring the sate-of-the-art parsers’ performance on robustness test sets, and evaluating the effect of data augmentation.
ISBN 9781954085022
Language eng
Indigenous content off
HERDC Research category E1 Full written paper - refereed
Persistent URL http://hdl.handle.net/10536/DRO/DU:30152880

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 21 Abstract Views, 6 File Downloads  -  Detailed Statistics
Created: Mon, 28 Jun 2021, 14:54:37 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.