Lexicalization Is All You Need: Examining the Impact of Lexical Knowledge in a Compositional QALD System

TL;DR

This paper demonstrates that explicit lexical knowledge significantly improves question answering over linked data, outperforming large language models in compositional interpretation and highlighting new research directions.

Contribution

It introduces a compositional QA system that leverages explicit lexical knowledge, achieving substantial performance gains over existing systems and revealing limitations of LLMs in this context.

Findings

Up to 35.8% increase in micro F1 score with lexical knowledge

Explicit lexical knowledge outperforms LLMs in compositional QA

LLMs show limited ability to interpret questions compositionally

Abstract

In this paper, we examine the impact of lexicalization on Question Answering over Linked Data (QALD). It is well known that one of the key challenges in interpreting natural language questions with respect to SPARQL lies in bridging the lexical gap, that is mapping the words in the query to the correct vocabulary elements. We argue in this paper that lexicalization, that is explicit knowledge about the potential interpretations of a word with respect to the given vocabulary, significantly eases the task and increases the performance of QA systems. Towards this goal, we present a compositional QA system that can leverage explicit lexical knowledge in a compositional manner to infer the meaning of a question in terms of a SPARQL query. We show that such a system, given lexical knowledge, has a performance well beyond current QA systems, achieving up to a $35.8\%$ increase in the micro $F_1$ score compared to the best QA system on QALD-9. This shows the importance and potential of including explicit lexical knowledge. In contrast, we show that LLMs have limited abilities to exploit lexical knowledge, with only marginal improvements compared to a version without lexical knowledge. This shows that LLMs have no ability to compositionally interpret a question on the basis of the meaning of its parts, a key feature of compositional approaches. Taken together, our work shows new avenues for QALD research, emphasizing the importance of lexicalization and compositionality.