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

Debayan Banerjee, Pranav Ajit Nair, Ricardo Usbeck, Chris Biemann
5/24/2023
cs.CL

No official code found. Best implementation: debayan/sparql-vocab-substitution (4 stars, last commit 2023-09-13).

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.

View on arXivView PDF

Code Implementations(1)

debayan/sparql-vocab-substitutionCommunity100%

Repository for ACL 2023 findings short paper titled "The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing"

40C, C++May 16, 20233 years ago

Similar Papers

Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding

83% match1 repo32023

Skeletons Matter: Dynamic Data Augmentation for Text-to-Query

83% match1 repo12025

Semantic Parsing for Conversational Question Answering over Knowledge Graphs

82% match1 repo192023

Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering

82% match1 repo632023

Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databases

82% match2023

A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges

82% match2024

Cite this paper

@article{banerjee2023role,
  title  = {The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing},
  author = {Debayan Banerjee and Pranav Ajit Nair and Ricardo Usbeck and Chris Biemann},
  year   = {2023},
  eprint = {2305.15108},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.15108v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.15108.svg)](https://codeofpaper.com/paper/2305.15108)

Discussion