Abstract
The identification of argument relation is an important subtask of argumentation mining. Its purpose is to identify the support or attack relationship between two argument components, so that people can understand the argument process in the argumentative text more deeply. This paper proposes a research method based on Scibert and BILSTM-CRF model. First, the pre-trained language model Scibert dynamically obtains word vectors, and then combines with the BiLSTM network to fine-tune downstream tasks to obtain contextual information. Finally, the argument relation is identified by conditional random field. Experiments were conducted on two argumentation mining datasets, Persuasive Essays and UKP Sentential Corpus, which were published in Germany. The experimental results show that our method is better than the baseline method.
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 callDisclaimer: 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.
