Ning Wang

Ning Wang


Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2020
Verified
Conference Paper
Closed access
SHShuang Hao
Shuang Hao
CCChengliang Chai
Chengliang Chai
Guoliang LiGuoliang Li
Guoliang Li
NTNan Tang
Nan Tang
NWNing Wang
Ning Wang
XYXiang Yu
Xiang Yu
Knowledge bases (KBs), which store high-quality information, are crucial for many applications, such as enhancing search results and serving as external sources for data cleaning. Not surprisingly, there exist outdated facts in most KBs due to the rapid change of information. Naturally, it is important to keep KBs up-to-date. Traditional wisdom has investigated the problem of using reference data (such as new facts extracted from the news) to detect outdated facts in KBs. However, existing approaches can only cover a small percentage of facts in KBs. In this paper, we propose a novel human-in-the-loop approach for outdated fact detection in KBs. It trains a binary classifier using features such as historical update frequency and existence time of a fact to compute the likelihood of a fact in a KB to be outdated. Then, it interacts with humans to verify whether a fact with high likelihood is indeed outdated. In addition, it also uses logical rules to detect more outdated facts based on human feedback. The outdated facts detected by the logical rules will also be fed back to train the ML model further for data augmentation. Extensive experiments on real-world KBs, such as Yago and DBpedia, show the effectiveness of our solution.

6 July 2022 in Entropy
Verified
Journal Article
Open access
PDF file
XWXiaoyu Wu
Xiaoyu Wu
NWNing Wang
Ning Wang
Error detection is a critical step in data cleaning. Most traditional error detection methods are based on rules and external information with high cost, especially when dealing with large-scaled data. Recently, with the advances of deep learning, some researchers focus their attention on learning the semantic distribution of data for error detection; however, the low error rate in real datasets makes it hard to collect negative samples for training supervised deep learning models. Most of the existing deep-learning-based error detection algorithms solve the class imbalance problem by data augmentation. Due to the inadequate sampling of negative samples, the features learned by those methods may be biased. In this paper, we propose an AEGAN (Auto-Encoder Generative Adversarial Network)-based deep learning model named SAT-GAN (Self-Attention Generative Adversarial Network) to detect errors in relational datasets. Combining the self-attention mechanism with the pre-trained language model, our model can capture semantic features of the dataset, specifically the functional dependency between attributes, so that no rules or constraints are needed for SAT-GAN to identify inconsistent data. For the lack of negative samples, we propose to train our model via zero-shot learning. As a clean-data tailored model, SAT-GAN tries to recognize error data as outliers by learning the latent features of clean data. In our evaluation, SAT-GAN achieves an average F1-score of 0.95 on five datasets, which yields at least 46.2% F1-score improvement over rule-based methods and outperforms state-of-the-art deep learning approaches in the absence of rules and negative samples.

1 July 2017 in International Journal of Digital Crime and Forensics
Verified
Journal Article
Closed access
PDF file
NWNing Wang
Ning Wang
As existing methods cannot express, share, and reuse the digital evidence review information in a unified manner, a solution of digital evidence review elements knowledge base model based on ontology is presented. Firstly, combing with the multi-source heterogeneous characteristic of digital evidence review knowledge, classification and extraction are accomplished. Secondly, according to the principles of ontology construction, the digital evidence review elements knowledge base model which includes domain ontology, application ontology, and atomic ontology is established. Finally, model can effectively acquire digital evidence review knowledge by analyzing review scenario.

1 June 2016 in International Journal of Software Engineering and Knowledge Engineering
Verified
Journal Article
Closed access
PDF file
NWNing Wang
Ning Wang
TTTian Tian
Tian Tian

27 February 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
SHShuang Hao
Shuang Hao
CCChengliang Chai
Chengliang Chai
Guoliang LiGuoliang Li
Guoliang Li
NTNan Tang
Nan Tang
NWNing Wang
Ning Wang
XYXiang Yu
Xiang Yu
Knowledge bases (KBs), which store high-quality information, are crucial for many applications, such as enhancing search results and serving as external sources for data cleaning. Not surprisingly, there exist outdated facts in most KBs due to the rapid change of information. Naturally, it is important to keep KBs up-to-date. Traditional wisdom has investigated the problem of using reference data (such as new facts extracted from the news) to detect outdated facts in KBs. However, existing approaches can only cover a small percentage of facts in KBs. In this paper, we propose HOFD , a novel human-in-the-loop approach for outdated fact detection in KBs. HOFD trains a binary classifier using features such as historical update frequency and update time of a fact to compute the likelihood of a fact in a KB to be outdated. Then, HOFD interacts with humans to verify whether a fact with high likelihood is indeed outdated. In addition, HOFD also uses logical rules to detect more outdated facts based on human feedback. The outdated facts detected by the logical rules will also be fed back to train the ML model further for data augmentation . Extensive experiments on real-world KBs, such as Yago and DBpedia, show the effectiveness of our solution.

1 January 2009
Verified
Conference Paper
Closed access
NKNathalie Cindy Kuicheu
Nathalie Cindy Kuicheu
NWNing Wang
Ning Wang
FNFanzou Tchuissang Gile Narcisse
Fanzou Tchuissang Gile Narcisse
DXDe Xu
De Xu
Francois SieweFrancois Siewe
Francois Siewe
Recently, the notion of Dataspace has been introduced as a virtual space where many data sources are managed regardless of their structures and locations; this, with the aim to return best efforts answers to user's queries. In fact, a dataspace is a set of participants which are data sources connected to the dataspace and a set of relationships between those participants. A data source, a participant, could be a file, a relational database, XML repository, web pages and so on. However, no formal definitions about relationships which could be built among the data sources have been proposed. Therefore, one of the challenges occurring in this new abstraction of data management is to incrementally build meaningful relationships between sources. In this paper, we introduce SEM-HDM, a SEMantics-based Heterogeneous Data Management which aims at constructing semantic relationships between heterogeneous sources of data based on a defined syntax and semantics. In fact, SEM-HDM first constructs a Semantic dictionary and then a reasoning dictionary which is improved incrementally by analyzing user's activities on a given dataspace. We show on an example of three heterogeneous sources of data how SEM-HDM builds his semantic and reasoning dictionary.