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.
Abstract (translated)
在本研究中,我们对文本到文本(T2T)模型中的输出词汇表在SPARQL语义解析任务中的作用进行了分析。我们在知识图问答(KGQA)的背景下进行了实验,该任务是将自然语言问题转换为SPARQL查询语言。我们观察到,查询词汇与人类词汇存在显著差异。语言模型(LMs)主要是针对人类语言任务进行训练的,因此,如果查询词汇被替换为更适应LM分割的单词,模型性能可能会提高。我们对查询进行了精心筛选的词汇替换,并在GrailQA数据集上发现了17%的绝对增益。
URL
https://arxiv.org/abs/2305.15108