# Conversational Lexicography: Querying Lexicographic Data on Knowledge Graphs with SPARQL through Natural Language

arXiv: https://arxiv.org/abs/2505.19971 · HTML: https://mlsanity.com/paper/2505.19971/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 37 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 11 of 11)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data](https://mlsanity.com/paper/2106.05006/) (2021)
- [Modern Baselines for SPARQL Semantic Parsing](https://mlsanity.com/paper/2204.12793/) (2022)
- [SPARQL as a Foreign Language](https://mlsanity.com/paper/1708.07624/) (2017)
- [Leveraging small language models for Text2SPARQL tasks to improve the resilience of AI assistance](https://mlsanity.com/paper/2405.17076/) (2024)
- [Neural Machine Translation for Query Construction and Composition](https://mlsanity.com/paper/1806.10478/) (2018)
- [A Chinese Multi-type Complex Questions Answering Dataset over Wikidata](https://mlsanity.com/paper/2111.06086/) (2021)
- [Monolingual alignment of word senses and definitions in lexicographical resources](https://mlsanity.com/paper/2209.02465/) (2022)

## Built on by (most cited first, 3 of 3)

- [Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filtering](https://mlsanity.com/paper/2605.10318/) (2026)
- [Toward Multi-Database Query Reasoning for Text2Cypher](https://mlsanity.com/paper/2605.10373/) (2026)
- [Introducing Human-Centeredness in AI-Assisted Lexicography](https://mlsanity.com/paper/2607.11808/) (2026)

## Abstract (arXiv)

Knowledge graphs offer an excellent solution for representing the lexical-semantic structures of lexicographic data. However, working with the SPARQL query language represents a considerable hurdle for many non-expert users who could benefit from the advantages of this technology. This paper addresses the challenge of creating natural language interfaces for lexicographic data retrieval on knowledge graphs such as Wikidata. We develop a multidimensional taxonomy capturing the complexity of Wikidata's lexicographic data ontology module through four dimensions and create a template-based dataset with over 1.2 million mappings from natural language utterances to SPARQL queries. Our experiments with GPT-2 (124M), Phi-1.5 (1.3B), and GPT-3.5-Turbo reveal significant differences in model capabilities. While all models perform well on familiar patterns, only GPT-3.5-Turbo demonstrates meaningful generalization capabilities, suggesting that model size and diverse pre-training are crucial for adaptability in this domain. However, significant challenges remain in achieving robust generalization, handling diverse linguistic data, and developing scalable solutions that can accommodate the full complexity of lexicographic knowledge representation.