基于依存句法分析的中文专利候选术语选取研究

[目的/意义]针对中文专利候选术语选取方法存在需要对不同的数据集分别制定不同的模式匹配规则、专利术语抽取准确性不高等问题,本文提出基于依存句法分析的中文专利术语选取方法,以提高中文专利术语抽取准确性。[方法/过程]主要包括依存句法分析、剪枝、生成依存子树等三个主要步骤。首先对中文专利进行依存句法分析,得到依存树,对依存树进行剪枝,去除不符合要求的依存关系,生成依存子树,从中选取连续词串作为候选术语,以抽取中文专利术语。[结果/结论]实验结果表明,与已有的中文专利候选术语选取方法相比,本文提出的基于依存句法分析的中文候选术语选取方法能够有效地提高中文专利术语抽取的准确性。

中文领域本体学习中术语的自动抽取

提出一种领域术语自动抽取的混合策略,首先进行多字词候选术语抽取和分词,然后合并其结果,最后通过领域相关度和领域主题一致度抽取出最终领域术语。在多字词抽取和最终领域术语抽取阶段分别对现有方法进行了改进,降低了字符串分解的时间复杂度并提高了领域术语抽取的准确率和召回率。实验表明,术语抽取准确率为90.64%,优于现有的抽取方法。

学术论文大纲中关键术语抽取方法研究

【目的】针对学术论文大纲内容精炼、层次性的特点,研究从中抽取重要且具有实质意义术语的方法。【方法】结合语言学规则和术语词典从大纲各级标题中识别出候选术语集,然后根据术语间的句法依存关系计算tf-idf,并利用大纲结构量化术语层级特征,最后结合tf-idf与层级特征对候选术语进行排名,选择出关键术语。【结果】实验证明,该方法的候选术语识别F值达到89.57%,术语选择F值达到36.89%。【局限】采用的术语抽取规则不完备,且tf-idf计算过程中的权值设置仅使用经验值,导致未能达到最优效果。【结论】该方法能有效抽取大纲中的关键术语,适用于层级结构中的关键术语抽取。

Studies on a Korean Buddhism Community： Searching for Unity Through Open Discourse

Korean Buddhism community has tried to develop its traditions as well as maintaining them through open discussion. Some current incidents, such as the election of the director for the headquarters of the Chogye Order, controversial issues on a prime minster nominee, and the difference between practicing and learning which has been discussed in Buddhist Academia, have generated a new wave in the Korean Buddhism world. Many religious practices which have infiltrated Korean society, including Catholicism and Christianity, have been indigenized to become a unique religious form combined with Korean Shamanism, through which individuals want to achieve personal happiness or material prosperity. Buddhism has been through the same process. Additionally, Buddhism has played a leading role in teaching the public of Korea for a long time and has become a model role for solving national crises. Currently, the Korean Buddhism world has tried to be reborn as a religion that keeps these beneficial traditions in Korea, and the Korean Buddhism can play a positive role in every aspect of culture, politics, and society. Further, the Korean Buddhism is looking for ways to influence Korean society through open discussions. This paper brings out issues that Korean Buddhism faces and presents the solutions to solve those problems.

基于登录词邻接关系的双条件概率的领域术语抽取算法

领域词典作为中文信息处理的基础,在各个领域都有着重要的应用.而人工构建领域词典不仅工作量大,而且缺乏时效性.因此,自动构建领域词典成为目前研究的重点,而构建领域词典的关键是从领域语料中自动抽取领域术语.本文以金融领域作为切入点,提出了根据登录词前后邻接关系计算邻接词之间的双条件概率自动识别领域术语.实验证明,本文提出的算法不仅能够有效地提取新术语,同时在小语料和低词频情况下也能取得较好的效果.

A new method for extracting domain terminology

This article proposes a new general, highly efficient algorithm for extracting domain terminologies. This domain-independent algorithm with multi-layers of filters is a hybrid of statistic-oriented and rule-oriented methods. Utilizing the features of domain terminologies and the characteristics that are unique to Chinese, this algorithm extracts domain terminologies by generating multi-word unit （MWU） candidates at first and then fihering the candidates through multi-strategies. Our test resuhs show that this algorithm is feasible and effective.