arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2501.16135cs.CL

面向多语言可配置数据到文本系统的NMT辅助语法迁移评估

Evaluation of NMT-Assisted Grammar Transfer for a Multi-Language Configurable Data-to-Text System

AX Semantics

Andreas Madsack, Johanna Heininger, Adela Schneider, Ching-Yi Chen, Christian Eckard, Robert Weißgraeber

AI总结:

本文提出一种基于规则的多语言NLG方法,通过NMT结合人工审查翻译语法配置,并引入跨语言语法依赖模型,实现无人工干预的文本生成扩展,在SportSett:Basketball数据集上验证了其语法正确性。

摘要:

多语言数据到文本生成的一种方法是预先将语法配置从源语言翻译到每种目标语言。这些配置随后被表层实现器和文档规划阶段使用以生成输出。在本文中,我们描述了该方法的基于规则的NLG实现,其中配置由神经机器翻译(NMT)结合一次性人工审查进行翻译,并引入跨语言语法依赖模型,创建一个从源数据生成文本的多语言NLG系统,在无人工干预的情况下扩展生成阶段。此外,我们提出了一种对自动翻译文本进行人工译后编辑评估的方法。我们在SportSett:Basketball数据集上的评估表明,我们的NLG系统表现良好,突显了其在翻译任务中的语法正确性。

英文摘要:

One approach for multilingual data-to-text generation is to translate grammatical configurations upfront from the source language into each target language. These configurations are then used by a surface realizer and in document planning stages to generate output. In this paper, we describe a rule-based NLG implementation of this approach where the configuration is translated by Neural Machine Translation (NMT) combined with a one-time human review, and introduce a cross-language grammar dependency model to create a multilingual NLG system that generates text from the source data, scaling the generation phase without a human in the loop. Additionally, we introduce a method for human post-editing evaluation on the automatically translated text. Our evaluation on the SportSett:Basketball dataset shows that our NLG system performs well, underlining its grammatical correctness in translation tasks.

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。

↑