The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing
This work addresses performance bottlenecks in semantic parsing for knowledge graph question answering, though it is incremental as it focuses on vocabulary optimization rather than a new method.
The paper tackles the problem of SPARQL semantic parsing for knowledge graph question answering by analyzing how output vocabulary affects text-to-text language models, finding that substituting query vocabulary with LM-tokenizer-friendly vocabulary yields absolute gains of 17% on the GrailQA dataset.
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.