Abstract
We propose a text classification model MNPC-BERT for marine natural product literature based on BERT pre-training model. The marking task of Masked LM performed at the input stage of the pre-training phase is moved to the encoder of the transformer, which solves the problem of inconsistency between the pre-training phase and the fine-tuning phase. We have constructed a data set from a number of literature data sources containing different types of marine natural products literature, as well as a variety of different types of non-marine natural products literature. Compared with the classical algorithm, the algorithm proposed in this paper can better complete the classification based on existing data set.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IOP Conference Series: Materials Science and Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
