paper-with-me

홈 › Papers

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

2023-05-24 · Debayan Banerjee, Pranav Ajit Nair, Ricardo Usbeck, Chris Biemann

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.

📄 PDF Abstract BibTeX arXiv:2305.15108

Code (1)

debayan/sparql-vocab-substitution 공식 구현 jax

Tasks

Graph Question AnsweringQuestion AnsweringSemantic Parsing

Similar Papers 제목 키워드 기반

Modern Baselines for SPARQL Semantic Parsing

2022-04-27 · Debayan Banerjee, Pranav Ajit Nair, Jivat Neet Kaur, Ricardo Usbeck 외

In this work, we focus on the task of generating SPARQL queries from natural language questions, which can then be executed on Knowledge Graphs (KGs). We assume that gold entity and relations have been provided, and the …

Knowledge GraphsSemantic Parsing

A Neural Approach to KGQA via SPARQL Silhouette Generation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Semantic parsing is a predominant approach to solve the Knowledge Graph Question Answering (KGQA) task where, natural language question is translated into a logic form such as SPARQL. Semantic parsing based …

Graph Question AnsweringMachine TranslationNMTQuestion Answering+3

Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training

2024-10-08 · Chang Su, Jiexing Qi, He Yan, Kai Zou 외

Semantic parsing that translates natural language queries to SPARQL is of great importance for Knowledge Graph Question Answering (KGQA) systems. Although pre-trained language models like T5 have achieved significant suc…

Graph Question AnsweringLanguage ModelingLanguage ModellingMasked Language Modeling+5

Semantic Parsing Natural Language into SPARQL: Improving Target Language Representation with Neural Attention

2018-03-12 · Fabiano Ferreira Luz, Marcelo Finger

Semantic parsing is the process of mapping a natural language sentence into a formal representation of its meaning. In this work we use the neural network approach to transform natural language sentence into a query to a…

Semantic ParsingSentence

GeoSPARQL+: Syntax, Semantics and System for Integrated Querying of Graph, Raster and Vector Data -- Technical Report

2020-09-10 · Timo Homburg, Steffen Staab, Daniel Janke

We introduce an approach to semantically represent and query raster data in a Semantic Web graph. We extend the GeoSPARQL vocabulary and query language to support raster data as a new type of geospatial data. We define n…