增量多语言文本到图结构的适配器组合
Incremental Multilingual Text2Cypher with Adapter Combination
AI总结：
本文提出一种可扩展的多语言文本到图结构方法，通过训练语言特定的LoRA适配器并结合统一线性融合或学习融合MLP，实现无需全量微调即可支持新语言，提升数据效率和性能。
摘要：
大型语言模型通过Text2SQL、Text2SPARQL和Text2Cypher等工具，使用户能用自然语言接口访问数据库。尽管这些系统提高了数据库的可访问性，但大多数研究集中在英语，多语言支持有限。本文研究了一种可扩展的多语言Text2Cypher方法，旨在支持新语言而无需重新运行全量微调，避免手动超参数调优，并保持性能接近联合多语言微调。我们为英语、西班牙语和土耳其语训练了语言特定的LoRA适配器，并通过统一线性融合或学习融合MLP结合。实验结果表明，融合MLP恢复了约75%的联合多语言微调的准确性提升，仅需更小的数据子集，在所有三种语言中均优于线性融合。该方法通过仅需一个LoRA适配器和轻量级MLP重新训练，实现了增量语言扩展。学习适配器融合为昂贵的联合微调提供了实用替代方案，平衡了性能、数据效率和可扩展性。
英文摘要：
Large Language Models enable users to access database using natural language interfaces using tools like Text2SQL, Text2SPARQL, and Text2Cypher, which translate user questions into structured database queries. While these systems improve database accessibility, most research focuses on English with limited multilingual support. This work investigates a scalable multilingual Text2Cypher, aiming to support new languages without re-running full fine-tuning, avoiding manual hyper-parameter tuning, and maintaining performance close to joint multilingual fine-tuning. We train language-specific LoRA adapters for English, Spanish, and Turkish and combined them via uniform linear merging or learned fusion MLP with dynamic gating. Experimental results show that the fusion MLP recovers around 75\% of the accuracy gains from joint multilingual fine-tuning while requiring only a smaller subset of the data, outperforming linear merging across all three languages. This approach enables incremental language expansion to new languages by requiring only one LoRA adapter and a lightweight MLP retraining. Learned adapter fusion offers a practical alternative to expensive joint fine-tuning, balancing performance, data efficiency, and scalability for multilingual Text2Cypher task.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
