The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing

Debayan Banerjee, Pranav Nair, Ricardo Usbeck, Chris Biemann


Abstract
In this work, we analyse the role of output vocabulary for text-to-text (T2T) models on the task of SPARQL semantic parsing. We perform experiments within the the context of knowledge graph question answering (KGQA), where the task is to convert questions in natural language to the SPARQL query language. We observe that the query vocabulary is distinct from human vocabulary. Language Models (LMs) are pre-dominantly trained for human language tasks, and hence, if the query vocabulary is replaced with a vocabulary more attuned to the LM tokenizer, the performance of models may improve. We carry out carefully selected vocabulary substitutions on the queries and find absolute gains in the range of 17% on the GrailQA dataset.
Anthology ID:
2023.findings-acl.774
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12219–12228
Language:
URL:
https://aclanthology.org/2023.findings-acl.774
DOI:
10.18653/v1/2023.findings-acl.774
Bibkey:
Cite (ACL):
Debayan Banerjee, Pranav Nair, Ricardo Usbeck, and Chris Biemann. 2023. The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12219–12228, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing (Banerjee et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.774.pdf