中文科技文献切分的领域适应技术研究

以生物医学文献为实例对象，研究科技文献切分中的领域适应技术，通过以词典特征、领域词汇特征、子串标注和使用词典切分的粗切分语料作为训练语料等方法，实现基于序列标注的中文切分方法由新闻领域到科技领域的适应，并取得了较好的效果。研究表明，在科技文献切分中，充分利用领域知识获取领域相关特征，对于提高科技文献切分的准确率具有重要的作用。

Research on Domain Adaptation Technology of Chinese Science and Technology Literatures Segmentation

Segmentation of science and technology (S&T) literature is a basic step in S&T documents information processing. This paper takes biomedical literatures as the instances and studies domain adaptation technology in segmentation of S&T literatures. Then it takes some methods such as dictionary features, domain character features, sub-word tagging and low quality in-domain training corpus based on dictionary-based segmentation to adapt Chinese segmentation method based on sequence labeling in journalism filed to S&T filed and achieves the significant improvement. It finds that how to exploit domain specific features with domain knowledge plays an important role in improving the segmentation quality of S&T literatures.