Knowledge Extraction From National Standards for Natural Resources

National standards for natural resources (NSNR) plays an important role in promoting efficient use of China's resources, which sets many domains such as marine and land resources. Its revision is difficult since different may overlap or conflict. To facilitate the NSNR, this paper extracts structural knowledge from NSNR files to assist its revision. are multi-domain texts, where traditional extraction methods could fall short recalling entities. address issue, proposes a method including sub-domain relation discovery (SRD) domain semantic features fusion (DSFF) module. SRD splits into sub-domains discovery. DSFF integrates conditional random field (CRF) model improve capability entity recognition. Experimental results demonstrate that proposed effectively extract NSNR.