Volltext-Downloads (blau) und Frontdoor-Views (grau)

Grammar-Constrained Neural Semantic Parsing with LR Parsers

  • Target meaning representations for semantic parsing tasks are often based on programming or query languages, such as SQL, and can be formalized by a context-free grammar. Assuming a priori knowledge of the target domain, such grammars can be exploited to enforce syntactical constraints when predicting logical forms. To that end, we assess how syntactical parsers can be integrated into modern encoder-decoder frameworks. Specifically, we implement an attentional SEQ2SEQ model that uses an LR parser to maintain syntactically valid sequences throughout the decoding procedure. Compared to other approaches to grammar-guided decoding that modify the underlying neural network architecture or attempt to derive full parse trees, our approach is conceptually simpler, adds less computational overhead during inference and integrates seamlessly with current SEQ2SEQ frameworks. We present preliminary evaluation results against a recurrent SEQ2SEQ baseline on GEOQUERY and ATIS and demonstrate improved performance while enforcing grammatical constraints.

Download full text files

Export metadata

Additional Services

Search Google Scholar Check availability


Show usage statistics
Document Type:Conference Object
Author:Artur Baranowski, Nico Hochgeschwender
Parent Title (English):Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
Number of pages:5
First Page:1275
Last Page:1279
Publisher:Association for Computational Linguistics
Place of publication:Stroudsburg, PA, USA
Publishing Institution:Hochschule Bonn-Rhein-Sieg
Date of first publication:2021/07/27
Copyright:ACL materials are Copyright © 1963–2021 ACL. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
Departments, institutes and facilities:Fachbereich Informatik
Institut für Cyber Security & Privacy (ICSP)
Dewey Decimal Classification (DDC):0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Entry in this database:2021/08/05
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International