arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.14447cs.CL
收藏

使用带双仿射分类器的深度神经网络分析越南语法律问题

Analyzing Vietnamese Legal Questions Using Deep Neural Networks with Biaffine Classifiers

Posts and Telecommunications Institute of Technology(邮电技术学院);FPT Technology Research Institute(FPT技术研究院);FPT University(FPT大学)

Nguyen Anh Tu, Hoang Thi Thu Uyen, Tu Minh Phuong, Ngo Xuan Bach

AI总结:

针对越南语法律问题信息提取任务,提出融合多特征、分三阶段且采用双仿射分类器的深度模型,在公开数据集上F1达94.79%,大幅优于现有工作。

摘要:

本文提出使用深度神经网络从越南语法律问题中提取重要信息,这是构建法律领域问答系统的一项基础任务。给定一个自然语言形式的法律问题,目标是提取所有包含回答问题所需信息的片段。我们提出一种深度模型,分三个阶段解决该任务。首先,模型利用近期先进的自编码语言模型生成上下文词嵌入,再将其与字符级信息、词性标注(POS-tag)信息结合,形成词表示。接下来,采用双向长短期记忆网络捕捉词与词之间的关系,生成句子级表示。在第三阶段,借鉴基于图的依存句法分析方法对输入句子提供全局视角的思路,我们使用双仿射分类器估计每一对起止词构成重要片段的概率。在一个公开越南语法律数据集上的实验结果表明,我们的模型大幅优于已有工作,F1值达到94.79%。该结果也证明,在有限数据集上训练时,结合从预训练语言模型中提取的上下文特征与字符级、词性标注等其他类型特征是有效的。

英文摘要:

In this paper, we propose using deep neural networks to extract important information from Vietnamese legal questions, a fundamental task towards building a question answering system in the legal domain. Given a legal question in natural language, the goal is to extract all the segments that contain the needed information to answer the question. We introduce a deep model that solves the task in three stages. First, our model leverages recent advanced autoencoding language models to produce contextual word embeddings, which are then combined with character-level and POS-tag information to form word representations. Next, bidirectional long short-term memory networks are employed to capture the relations among words and generate sentence-level representations. At the third stage, borrowing ideas from graph-based dependency parsing methods which provide a global view on the input sentence, we use biaffine classifiers to estimate the probability of each pair of start-end words to be an important segment. Experimental results on a public Vietnamese legal dataset show that our model outperforms the previous work by a large margin, achieving 94.79% in the F1 score. The results also prove the effectiveness of using contextual features extracted from pre-trained language models combined with other types of features such as character-level and POS-tag features when training on a limited dataset.

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。

↑