arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.00210cs.CL
收藏

利用上下文感知规则注入改进形式化风格转换

Improving Formality Style Transfer with Context-Aware Rule Injection

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校)

Zonghai Yao, Hong Yu

摘要:

在大规模常规文本语料库上预训练的模型通常不能很好地用于语言风格与主流文本显著不同的用户生成的数据。在这里,我们提出了上下文感知的规则注入(CARI),一种创新的方法,正式的风格转移(FST)。CARI将多个规则注入到端到端基于BERT的编码器和解码器模型中。它学习根据上下文选择最佳规则。内在评估表明,CARI在FST基准数据集上实现了新的最高性能。我们的外部评估表明,CARI可以大大提高常规预训练模型在几个推文情感分析任务上的性能。

英文摘要:

Models pre-trained on large-scale regular text corpora often do not work well for user-generated data where the language styles differ significantly from the mainstream text. Here we present Context-Aware Rule Injection (CARI), an innovative method for formality style transfer (FST). CARI injects multiple rules into an end-to-end BERT-based encoder and decoder model. It learns to select optimal rules based on context. The intrinsic evaluation showed that CARI achieved the new highest performance on the FST benchmark dataset. Our extrinsic evaluation showed that CARI can greatly improve the regular pre-trained models' performance on several tweet sentiment analysis 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。

↑