用统一语义表示生成多语言文本，仅靠少量标注数据就达到良好效果。
Generating Text from Uniform Meaning Representation
- 将UMR图直接输入现有AMR生成模型，作为基线方法
- 通过转换和微调，英文与中文生成得分分别达0.825和0.882
- 为少样本场景下的多语言语义生成提供可行路径，适合语义研究者
统一语义表示（UMR）是一种基于图的语义表征，相较于抽象语义表示（AMR），在文档级信息融合与多语言兼容性方面有显著拓展。尽管当前可用的UMR标注数据极少，本文首次探索从多语言UMR图生成文本的方法。利用UMR与AMR在结构上的相似性及丰富的AMR技术资源，提出三种策略：（1）直接将UMR图输入AMR-to-text模型；（2）先将UMR转换为AMR，再使用现有模型；（3）基于UMR数据对基础模型和AMR生成模型进行微调。实验表明，最优模型在英文和中文上的多语言BERTscore分别达到0.825和0.882，验证了微调方法在有限数据下仍具有效性。
原文摘要 · Abstract (English)
Uniform Meaning Representation (UMR) is a recently developed graph-based semantic representation, which expands on Abstract Meaning Representation (AMR) in a number of ways, in particular through the inclusion of document-level information and multilingual flexibility. In order to effectively adopt and leverage UMR for downstream tasks, efforts must be placed toward developing a UMR technological ecosystem. Though only a small amount of UMR annotations have been produced to date, in this work, we investigate the first approaches to producing text from multilingual UMR graphs. Exploiting the structural similarity between UMR and AMR graphs and the wide availability of AMR technologies, we introduce (1) a baseline approach which passes UMR graphs to AMR-to-text generation models, (2) a pipeline conversion of UMR to AMR, then using AMR-to-text generation models, and (3) a fine-tuning approach for both foundation models and AMR-to-text generation models with UMR data. Our best performing models achieve multilingual BERTscores of 0.825 for English and 0.882 for Chinese, a promising indication of the effectiveness of fine-tuning approaches for UMR-to-text generation even with limited UMR data.
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。