WZWanli Zuo

Wanli Zuo

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wanli Zuo has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Label-aware Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding

    by Shining Liang, Linjun Shou, Jian Pei, Ming Gong, Wanli Zuo, Xianglin Zuo, Daxin Jiang

    Despite the great success of spoken language understanding (SLU) in high-resource languages, it remains challenging in low-resource languages mainly due to the lack of labeled training data. The recent multilingual code-switching approach achieves better alignments of model representations across languages by constructing a mixed-language context in zero-shot cross-lingual SLU. However, current code-switching methods are limited to implicit alignment and disregard the inherent semantic structure in SLU, i.e., the hierarchical inclusion of utterances, slots, and words. In this paper, we propose to model the utterance-slot-word structure by a multi-level contrastive learning framework at the utterance, slot, and word levels to facilitate explicit alignment. Novel code-switching schemes are introduced to generate hard negative examples for our contrastive learning framework. Furthermore, we develop a label-aware joint model leveraging label semantics to enhance the implicit alignment and feed to contrastive learning. Our experimental results show that our proposed methods significantly improve the performance compared with the strong baselines on two zero-shot cross-lingual SLU benchmark datasets.

  • Open Access

    CalibreNet: Calibration Networks for Multilingual Sequence Labeling

    by Shining Liang, Linjun Shou, Jian Pei, Ming Gong, Wanli Zuo, Daxin Jiang

    Lack of training data in low-resource languages presents huge challenges to sequence labeling tasks such as named entity recognition (NER) and machine reading comprehension (MRC). One major obstacle is the errors on the boundary of predicted answers. To tackle this problem, we propose CalibreNet, which predicts answers in two steps. In the first step, any existing sequence labeling method can be adopted as a base model to generate an initial answer. In the second step, CalibreNet refines the boundary of the initial answer. To tackle the challenge of lack of training data in low-resource languages, we dedicatedly develop a novel unsupervised phrase boundary recovery pre-training task to enhance the multilingual boundary detection capability of CalibreNet. Experiments on two cross-lingual benchmark datasets show that the proposed approach achieves SOTA results on zero-shot cross-lingual NER and MRC tasks.

  • Open Access

    A Block-based Generative Model for Attributed Networks Embedding

    by Xueyan Liu, Bo Yang, Wenzhuo Song, Katarzyna Musial, Wanli Zuo, Hongxu Chen, Hongzhi Yin

    Attributed network embedding has attracted plenty of interest in recent years. It aims to learn task-independent, low-dimensional, and continuous vectors for nodes preserving both topology and attribute information. Most of the existing methods, such as random-walk based methods and GCNs, mainly focus on the local information, i.e., the attributes of the neighbours. Thus, they have been well studied for assortative networks (i.e., networks with communities) but ignored disassortative networks (i.e., networks with multipartite, hubs, and hybrid structures), which are common in the real world. To enable model both assortative and disassortative networks, we propose a block-based generative model for attributed network embedding from a probability perspective. Specifically, the nodes are assigned to several blocks wherein the nodes in the same block share the similar linkage patterns. These patterns can define assortative networks containing communities or disassortative networks with the multipartite, hub, or any hybrid structures. To preserve the attribute information, we assume that each node has a hidden embedding related to its assigned block. We use a neural network to characterize the nonlinearity between node embeddings and node attributes. We perform extensive experiments on real-world and synthetic attributed networks. The results show that our proposed method consistently outperforms state-of-the-art embedding methods for both clustering and classification tasks, especially on disassortative networks.

  • Open Access

    IDDSAM: An Integrated Disease Diagnosis and Severity Assessment Model for Intensive Care Units

    by Zhenkun Shi, Wanli Zuo, Shining Liang, Xianglin Zuo, Lin Yue, Xue Li

    People are admitted to intensive care units (ICUs) because they need complete support for failing organ systems, constant monitoring, routine nursing care, and treatment. A critical or intensive illness is different from conventional or chronic diseases that most people are likely to have previously encountered. Such an illness is often unexpected and without warnings and can suddenly strike the previously fit. High levels of treatment and support are generally required to prevent life-threatening complications for the patents. Two of the most noticeable actions during an ICU stay are disease diagnosis and severity assessment of the patients. Unlike the majority of previous approaches where diagnosis and severity assessment are studied separately, we treat these actions as two tasks in an integrated procedure that clinicians must be able to quickly and accurately conduct such that patients are given the best possible chance for therapeutic success. In this paper, we propose an integrated disease diagnosis and severity assessment model (IDDSAM) to diagnose and assess diseases. Moreover, accompanying the prediction, we also provide an evidence-based explanation. IDDSAM is a multisource multitask model that is based on an attention mechanism and utilizes shareable information from laboratory tests, bedside monitoring, and complications to support patients’ severity assessment and in-hospital disease diagnoses. We use 50,430 ICU cases consisting of 46,520 patients from 50 kinds of diseases over nine classifications to evaluate our proposed model. The experimental results demonstrated that our model outperforms the existing state-of-the-art mortality and diagnosis prediction framework by 3.79% on average in terms of accuracy for the mortality prediction tasks and by 14.51% on average for the diagnosis tasks.


  • Jointly Image Annotation and Classification Based on Supervised Multi-Modal Hierarchical Semantic Model

    by Chun-Yan Yin, Yong-Heng Chen, Wan-Li Zuo

    A lot of applications involve capturing correlations from multi-modality data, where available information spans multiple modalities, such as text, images or speech. In this paper, we pay attention to the specific case in which images are both labeled with a category and annotated with free text, and develop a supervised multi-modal hierarchical semantic model (smHSM), where we incorporate image classification into the joint modeling of visual and textual information, for the tasks of image annotation and classification. To evaluate the effectiveness of our model, we experiment our model on two datasets, and compare with other traditional models. The results demonstrate the effectiveness and advantages of our model in caption perplexity, classification accuracy and image annotation accuracy.


  • Deep Latent Factor Model with Hierarchical Similarity Measure for recommender systems

    by Jiayu Han, Lei Zheng, He Huang, Yuanbo Xu, Philip S. Yu, Wanli Zuo


  • Statistical Analysis for Detection of Sensitive Data Using Hadoop Clusters

    by Binod Kumar Adhikari, Wanli Zuo, Ramesh Maharjan, Xuming Han, Prakash Bahadur Amatya, Wajid Ali

    The omnipresence of internet technology and the advent of smart devices accumulate varieties of voluminous, viscous real-time data in a network from varieties of sources and also facilitates a way for criminal, intruders to attack the network which persuades information theft, financial loss, cyber-attack, and cyberwar. It is the major challenge for researchers to determine sensitive data from large scale real-time data so that the right action can be taken at the right time. Therefore, it is important to purpose a framework to handle massive data and to detect sensitive data from big data. In this regard, the collected data from the network are stored in cloud drives, other storage devices and then transferred to Hadoop distributed file system and processed with MapReduce processing using distributed computing concepts, Machine learning algorithms, and advanced statistical methods. Statistical analytical tools like Descriptive Analysis, Regression, ANOVA, Parametric Levene's test, Pearson Correlation, and Kruskal-Wallis Test present that recent big data analytical tools are effective than the traditional method for retrieval of sensitive data from Big Data.


  • Open Access

    Sentiment-Aspect Analysis through Semi-Supervised Topic Modeling

    by Yong Heng Chen, Wanli Zuo, Hao Yue, Yaojin Lin