TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Baranowski, Artur
A1  - Hochgeschwender, Nico
T1  - Grammar-Constrained Neural Semantic Parsing with LR Parsers
T2  - Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
N2  - 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.
UN  - https://nbn-resolving.org/urn:nbn:de:hbz:1044-opus-57802
SN  - 978-1-954085-54-1
SB  - 978-1-954085-54-1
U6  - https://doi.org/10.18653/v1/2021.findings-acl.108
DO  - https://doi.org/10.18653/v1/2021.findings-acl.108
SP  - 1275
EP  - 1279
S1  - 5
PB  - Association for Computational Linguistics
CY  - Stroudsburg, PA, USA
ER  -