The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering
Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking
From Roots to Rewards: Dynamic Tree Reasoning with RL
Describe Anything Model for Visual Question Answering on Text-rich Images
Warehouse Spatial Question Answering with LLM Agent
L0: Reinforcement Learning to Become General Agents
토론
이 논문과 연결된 포럼 글이 아직 없습니다.