Design of Intelligent QA for Self-learning of College Students Based on BERT

Konferenz: ISCTT 2021 - 6th International Conference on Information Science, Computer Technology and Transportation
26.11.2021 - 28.11.2021 in Xishuangbanna, China

Tagungsband: ISCTT 2021

Seiten: 5Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Gu, Zongyun; Wang, Qing; Li, Fangfang; Ou, Yangting (College of Medical Information Engineering, Anhui University of Traditional Chinese Medicine, Hefei, China)

With the continuous changes in the social environment, educational concepts, training goals, and teaching conditions under the new situation, the ability of self-learning has become a key ability for college students to deal with various challenges. The biggest problem of self-learning for college students is that they cannot be solved in real time, accurately and effectively when they encounter problems. To solve this problem, we propose a self-learning intelligent question answering system based on NLP. The system uses the BERT pre-training model to extract the representation of the input sequence, and then transmits the representation to each layer of the encoder and decoder of the downstream NMT model through the attention mechanism, and finally connects to the BERT-fused model. The model was trained and tested on the open source datasets MedQuAD and cMedQA2. The BLUE VALUES reached 42.21% and 44.55% respectively, which was significantly higher than other models.