Modal Dependency Parsing via Language Model Priming
Modal Dependency Parsing via Language Model Priming
复制标题
DOI：
10.18653/v1/2022.naacl-main.211
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Jiarui Yao;Nianwen Xue;Bonan Min
中科院分区：
文献类型：
--
作者：
Jiarui Yao;Nianwen Xue;Bonan Min
模态依赖解析的任务是将文本解析为其模态依赖结构，该结构是文本中事件真实性的表示。我们设计了一个基于启动预训练语言模型的模态依赖解析器，并在两个数据集上对解析器进行了评估。与基线相比，我们显示英语和中文的f分数分别提高了2.6%和4.6%。据我们所知，这也是第一个关于汉语情态依赖分析的工作。
The task of modal dependency parsing aims to parse a text into its modal dependency structure, which is a representation for the factuality of events in the text. We design a modal dependency parser that is based on priming pre-trained language models, and evaluate the parser on two data sets. Compared to baselines, we show an improvement of 2.6% in F-score for English and 4.6% for Chinese. To the best of our knowledge, this is also the first work on Chinese modal dependency parsing.