mlsanityData to 14 Oct 2026

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

arXiv 2305.15108 ↗First posted 24 May 2023cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

14 of 24 references.

References · 14

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 905
  7. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 171
  8. 2021OpenPrompt: An Open-source Framework for Prompt-learningcited by 148
  9. 2020Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsingcited by 72
  10. 2022Modern Baselines for SPARQL Semantic Parsingcited by 34
  11. 2022XPrompt: Exploring the Extreme of Prompt Tuningcited by 30
  12. 2021The Power of Prompt Tuning for Low-Resource Semantic Parsingcited by 21
2 more
  1. 2022Unfreeze with Care: Space-Efficient Fine-Tuning of Semantic Parsing Modelscited by 4
  2. 2022PIZZA: A new benchmark for complex end-to-end task-oriented parsingcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025InteracSPARQL: An Interactive System for SPARQL Query Refinement Using Natural Language Explanationscited by 2