用源语言语义表示生成目标语言句子，解决零资源语义解析难题
Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing
- 基于多语言模型的表征几何，从源语言语义码生成目标语言句子
- 在两个基准上实现显著性能提升，槽位值对齐率高且语义完整
- 仅需源语言标注数据和单语语料，适合无资源语言的语义解析应用
近期研究尝试利用多语言预训练语言模型（mPLMs）扩展跨语言语义解析（SP），无需大量标注数据。然而，在零样本跨语言迁移中仍存在性能差距。本文提出跨语言反解析（CBP），一种新颖的数据增强方法，旨在提升跨语言语义解析的迁移效果。该方法利用mPLMs的表征几何特性，从源语言意义表示中合成目标语言话语。仅需源语言标注数据与单语语料库，便可在零资源场景下有效实现跨语言数据增强。在两个跨语言语义解析基准（Mschema2QA 和 Xspider）上的大量实验表明，CBP在目标语言上带来显著性能提升。对生成话语的进一步分析显示，该方法能以高槽位值对齐率生成保持语义完整的句子。代码与数据已公开于 https://github.com/deokhk/CBP。
原文摘要 · Abstract (English)
Recent efforts have aimed to utilize multilingual pretrained language models (mPLMs) to extend semantic parsing (SP) across multiple languages without requiring extensive annotations. However, achieving zero-shot cross-lingual transfer for SP remains challenging, leading to a performance gap between source and target languages. In this study, we propose Cross-Lingual Back-Parsing (CBP), a novel data augmentation methodology designed to enhance cross-lingual transfer for SP. Leveraging the representation geometry of the mPLMs, CBP synthesizes target language utterances from source meaning representations. Our methodology effectively performs cross-lingual data augmentation in challenging zero-resource settings, by utilizing only labeled data in the source language and monolingual corpora. Extensive experiments on two cross-language SP benchmarks (Mschema2QA and Xspider) demonstrate that CBP brings substantial gains in the target language. Further analysis of the synthesized utterances shows that our method successfully generates target language utterances with high slot value alignment rates while preserving semantic integrity. Our codes and data are publicly available at https://github.com/deokhk/CBP.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。