YWYing Wang

Ying Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ying Wang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Enhanced Semantic BERT for Named Entity Recognition in Education

    by Ping Huang, Huijuan Zhu, Ying Wang, Lili Dai, Lei Zheng

    To address the technical challenges in the educational domain named entity recognition (NER), such as ambiguous entity boundaries and difficulties with nested entity identification, this study proposes an enhanced semantic BERT model (ES-BERT). The model innovatively adopts an education domain, vocabulary-assisted semantic enhancement strategy that (1) applies the term frequency–inverse document frequency (TF-IDF) algorithm to weight domain-specific terms, and (2) fuses the weighted lexical information with character-level features, enabling BERT to generate enriched, domain-aware, character–word hybrid representations. A complete bidirectional long short-term memory-conditional random field (BiLSTM-CRF) recognition framework was established, and a novel focal loss-based joint training method was introduced to optimize the process. The experimental design employed a three-phase validation protocol, as follows: (1) In a comparative evaluation using 5-fold cross-validation on our proprietary computer-education dataset, the proposed ES-BERT model yielded a precision of 90.38%, which is higher than that of the baseline models; (2) Ablation studies confirmed the contribution of domain-vocabulary enhancement to performance improvement; (3) Cross-domain experiments on the 2016 knowledge base question answering datasets and resume benchmark datasets demonstrated outstanding precision of 98.41% and 96.75%, respectively, verifying the model’s transfer-learning capability. These comprehensive experimental results substantiate that ES-BERT not only effectively resolves domain-specific NER challenges in education but also exhibits remarkable cross-domain adaptability.


  • A Multi-Bandwidth Local Feature Enhanced Sentiment Analysis Model Based on BERT

    by Ping Huang, Huijuan Zhu, Fengqin You, Ying Wang, Lili Dai, Lei Zheng

    The reliance on global feature modeling in BERT’s encoding process may lead to an oversight of actual feature correlations, thereby limiting the model’s classification performance. To address this limitation, we propose the MLFE-BERT model, which integrates Multi-bandwidth Local Feature Enhancement (MLFE) into BERT for sentiment analysis tasks. The model combines multi-bandwidth pooling operations with locally enhanced linear embedding techniques to amplify textual local features. Additionally, it leverages BERT’s multi-head attention mechanism to capture nuanced semantic information, thereby enriching the model’s contextual representations. Furthermore, to address the challenge of imbalanced sample distributions, the model incorporates a novel Dynamic Balance Representation (DBR) joint training strategy. This strategy simultaneously optimizes cross-entropy loss and focal loss, enabling the model to adapt more effectively to complex data distributions. Consequently, the model’s generalization ability and classification accuracy are significantly improved. Experiments on three public datasets demonstrate that the proposed MLFE-BERT model, with its MLFE and joint training strategy, outperforms the baseline BERT model in sentiment classification tasks. The results show consistent improvements in precision, [ ]-score and recall, confirming the feasibility and effectiveness of the proposed method.