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

Source: [The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing](<https://www.sota2.com/research/paper/68fa6f7d1e209131cea45ee8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:30:18.237Z

Authors: Debayan Banerjee, Pranav Ajit Nair, Ricardo Usbeck, Chris Biemann

Published: 2023-05-24T12:55:04.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2305.15108>)

[PDF](<https://arxiv.org/pdf/2305.15108.pdf>)

[Implementation](<https://github.com/debayan/sparql-vocab-substitution>)
