关键词: 技术名称识别, 成分句法分析, 无监督方法, 成分句法树, 术语抽取

Abstract: Technology terms are used to communicate accurate information. Automatically identifying technology terms from text can help experts and the public to discover, recognize, and apply new technologies, which is great of value. As one of mainstream approaches, unsupervised technology terms recognition methods still have some limitations, such as complex rules and poor adaptability. To enhance the ability to recognize technology terms from text, an unsupervised technical term recognition method was proposed. Firstly, a syntactic structure tree was constructed through constituency parsing. Then, the candidate technology terms were extracted from both top-down and bottom-up perspectives. Finally, the statistical frequency and semantic information were combined to determine the most appropriate technology terms. Besides, a technology term dataset was constructed to validate the effectiveness of the proposed method. Experimental results on the proposed dataset show that has the F1 score improved by 7.62 percentage points compared to traditional dependency-based methods. MeanWhile, the analysis results conducted on case study in the field of 3D Printing show that the identified technology terms are in line with the development of the field, which can be used to trace the development process of technology and depict the evolution path of technology, so as to provide references for understanding, discovering, and exploring future technologies.

Key words: technology term recognition, constituency parsing, unsupervised method, constituent parse tree, term extraction