YHYongzhong Huang

Yongzhong Huang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yongzhong Huang has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Twitter stance detection using deep learning model with FastText Embedding

    by Yongqing Deng, Yongzhong Huang

    The interactivity of social media platforms allows a large number of users to comment on different political or social issues to express their views, and identifying users' stances from online comment texts helps the government to monitor public opinion more effectively. The automatic recognition of stance information in comment text has become a new research hotspot in the field of natural language processing. Most of the existing text stance analysis corpus focuses on political topics in European and American countries, and high-quality stance analysis corpus research on political topics in Southeast Asian countries is relatively scarce. In order to stimulate this research direction, this paper provides a dataset about the 2022 Philippine presidential election, which annotates the stance information of the two popular presidential candidates and provides reliable data support for subsequent stance analysis model research. Next, we build a stance detection model of hybrid deep neural networks based on BiLSTM, CNN, and Attention, and we demonstrate its effectiveness on multiple datasets and obtain the best results on the SemEval-2016 dataset. In addition, we compare FastText and Word2Vec, two pre-trained word embeddings for word encoding, and discuss which word embedding is preferred in stance detection tasks. This result shows that the stance analysis model proposed in this paper can be effectively applied to Twitter text stance data.


  • Open Access

    Efficient Estimate of Sentence's Representation Based on the Difference Semantics Model

    by Xianwen Liao, Yongzhong Huang, Yongzhuang Wei, Chenhao Zhang, Fu Wang, Yong Wang

    Sentence representation is an important research hotspot in natural language processing (NLP) since it can map the semantics of sentences into semantics vectors, thereby effectively solving complex semantics computing problems. Recently, sentence representations are mainly obtained by indirect means. Specifically, for sentence representations obtained by unsupervised means, they are often calculated by the weighted sum of embeddings of tokens in sentences; for sentence representations obtained by self-supervised or supervised means, they are often derived from intermediate encodings of sentences in prediction tasks. For example, Google's BERT and MUSE respectively use the embedding of [CLS] in the next sentence prediction task and intermediate encodings of sentences in the translation bridge task as sentence representations. In this paper, we use the observed semantics increment feature of sentences to directly model the semantics function of sentences. To be able to use the existing neural network language model to approximate the semantics function, we first implement the first-order Taylor expansion on the semantics function to obtain a difference semantics model and then add it to BERT as a subtask to perform self-supervised fine-tuning. Finally, we get a new sentence representation model S-BERT. S-BERT achieves the state-of-the-art performance on many datasets in Chinese, English, and Vietnamese.


  • Open Access

    Research on Traffic Classification of Auto Machine-learning Base on Meta-QNN

    by Xin Yu Xu, Yong Zhong Huang, Yong Cheng Luo, Guige Ouyang, Haoyu Zhuang

    The traditional traffic classification task relies on feature engineering by experts with specialized knowledge. With the advent of representation-learn-based traffic classification techniques, machines learned to extract features from traffic data and classify them. In this paper, we research traffic classification technology based on representational learning and import auto-machine learning technology to solve the problems of network architecture design and parameter tuning. We also design a befitting reward function for the network architecture model. The experimental results on the USTC-TF2016 dataset and USTC-TF2016-PLUS shows that the network architecture generated by auto-machine learning technology has better training performance and classification accuracy than a traditional neural network.


  • Open Access

    Word Embedding With Zipf’s Context

    by Lizheng Gao, Gang Zhou, Junyong Luo, Yongzhong Huang

    Word embeddings generated by neural language models have achieved great success in many NLP tasks. However, neural language models may be difficult to train and time consuming. In this paper, we introduce a simpler but efficient word embedding method based on cooccurrence matrix factorization. Our method drastically reduces the dimensions of the cooccurrence matrix according to the famous Zipf's word frequency law. We observe that if the sampling times of a target word increase to a certain extent, the context of the target word will follow the Zipf's distribution. Enlightened by this, we propose a novel transformation for the cooccurrence matrix. The built cooccurrence matrix is then factorized by PCA. As PCA simply factorizes the cooccurrence matrix linearly and cannot capture the nonlinear relations of features, we construct an autoencoder to further transform the vectors. We compare our method with some well-known neural language models. Our method shows a comparable performance though it is much simpler than the neural language models.


  • Open Access

    ELPKG: A High-Accuracy Link Prediction Approach for Knowledge Graph Completion

    by Jiangtao Ma, Yaqiong Qiao, Guangwu Hu, Yanjun Wang, Chaoqin Zhang, Yongzhong Huang, Arun Kumar Sangaiah, Huaiguang Wu, Hongpo Zhang, Kai Ren

    Link prediction in knowledge graph is the task of utilizing the existing relations to infer new relations so as to build a more complete knowledge graph. The inferred new relations plus original knowledge graph is the symmetry of completion knowledge graph. Previous research on link predication only focuses on path or semantic-based features, which can hardly have a full insight of features between entities and may result in a certain ratio of false inference results. To improve the accuracy of link predication, we propose a novel approach named Entity Link Prediction for Knowledge Graph (ELPKG), which can achieve a high accuracy on large-scale knowledge graphs while keeping desirable efficiency. ELPKG first combines path and semantic-based features together to represent the relationships between entities. Then it adopts a probabilistic soft logic-based reasoning method that effectively solves the problem of non-deterministic knowledge reasoning. Finally, the relation between entities is completed based on the entity link prediction algorithm. Extensive experiments on real dataset show that ELPKG outperforms baseline methods on hits@1, hits@10, and MRR.


  • Memory latency optimizations for the elementary functions on the Sunway architecture

    by Bei Zhou, Yongzhong Huang, Jinchen Xu, Shaozhong Guo, Hongyuan Qi