Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (1031)
- Computer Sciences (1030)
- Databases and Information Systems (510)
- Artificial Intelligence and Robotics (316)
- Software Engineering (185)
-
- Graphics and Human Computer Interfaces (150)
- Numerical Analysis and Scientific Computing (142)
- Social and Behavioral Sciences (106)
- Programming Languages and Compilers (103)
- Communication (87)
- Social Media (79)
- Engineering (58)
- Computer Engineering (43)
- Business (30)
- Information Security (30)
- Theory and Algorithms (28)
- Data Storage Systems (25)
- Education (22)
- OS and Networks (18)
- E-Commerce (12)
- Medicine and Health Sciences (11)
- Operations Research, Systems Engineering and Industrial Engineering (11)
- Higher Education (10)
- Arts and Humanities (7)
- Asian Studies (7)
- Digital Communications and Networking (7)
- Health Information Technology (7)
- International and Area Studies (7)
- Educational Assessment, Evaluation, and Research (6)
- Finance and Financial Management (6)
- Keyword
-
- Social media (36)
- Deep learning (25)
- Natural language processing (22)
- Large Language Models (19)
- LLMs (18)
-
- Machine learning (18)
- Large language models (17)
- Twitter (15)
- Sentiment analysis (14)
- Software engineering (13)
- Text mining (13)
- Computational linguistics (11)
- Neural networks (11)
- Natural Language Processing (10)
- Language model (9)
- Data mining (8)
- Deep Learning (8)
- Large Language Model (8)
- Large language model (8)
- Semantics (8)
- Artificial intelligence (7)
- Generative AI (7)
- Information retrieval (7)
- Question answering (7)
- Reinforcement learning (7)
- Transformer (7)
- Clustering (6)
- Graph neural networks (6)
- Multimodal (6)
- Natural language processing systems (6)
- Publication Year
Articles 1021 - 1047 of 1047
Full-Text Articles in Entire DC Network
Cuhk At Imageclef 2005: Cross-Language And Cross Media Image Retrieval, Steven Hoi, Jianke Zhu, Michael R. Lyu
Cuhk At Imageclef 2005: Cross-Language And Cross Media Image Retrieval, Steven Hoi, Jianke Zhu, Michael R. Lyu
Research Collection School Of Computing and Information Systems
In this paper, we describe our studies of cross-language and cross-media image retrieval at the ImageCLEF 2005. This is the first participation of our CUHK (The Chinese University of Hong Kong) group at ImageCLEF. The task in which we participated is the “bilingual ad hoc retrieval” task. There are three major focuses and contributions in our participation. The first is the empirical evaluation of language models and smoothing strategies for cross-language image retrieval. The second is the evaluation of cross-media image retrieval, i.e., combining text and visual contents for image retrieval. The last is the evaluation of bilingual image retrieval …
Understanding Intrinsic Factors Influencing Benefit Maximization Of Is Usage, Brenda Eschenbrenner, Fiona Fui-Hoon Nah
Understanding Intrinsic Factors Influencing Benefit Maximization Of Is Usage, Brenda Eschenbrenner, Fiona Fui-Hoon Nah
Research Collection School Of Computing and Information Systems
This research uses the Repertory Grid technique to understand intrinsic factors influencing benefit maximization of IS usage. The results show that domain-relevant skills, task motivation, cognitive/work style attributes, individual characteristics (identified as creativity traits) and personal characteristics (identified as innovativeness traits) influence benefit maximization of IS usage. The findings not only provide insights on ways to increase quality of IS usage in organizations but are also helpful for identifying approaches that foster attributes leading to increased benefit realization from IS usage.
Exploiting Domain Structure For Named Entity Recognition, Jing Jiang, Chengxiang Zhai
Exploiting Domain Structure For Named Entity Recognition, Jing Jiang, Chengxiang Zhai
Research Collection School Of Computing and Information Systems
Named Entity Recognition (NER) is a fundamental task in text mining and natural language understanding. Current approaches to NER (mostly based on supervised learning) perform well on domains similar to the training domain, but they tend to adapt poorly to slightly different domains. We present several strategies for exploiting the domain structure in the training data to learn a more robust named entity recognizer that can perform well on a new domain. First, we propose a simple yet effective way to automatically rank features based on their generalizabilities across domains. We then train a classifier with strong emphasis on the …
Improving The Quality Of Conceptual Modeling Using Cognitive Mapping Techniques, Keng Siau, X. Tan
Improving The Quality Of Conceptual Modeling Using Cognitive Mapping Techniques, Keng Siau, X. Tan
Research Collection School Of Computing and Information Systems
Conceptual modeling involves the understanding and communication between system analysts and end-users. Many factors may affect the quality of conceptual modeling processes as well as the models per se. Human cognition plays a pivotal role in understanding these factors and cognitive mapping techniques are effective tools to elicit and represent human cognition. In this paper, we look at the use of cognitive mapping techniques to improve the quality of conceptual modeling. We review frameworks on quality in conceptual modeling and examine the role of human cognition in conceptual modeling. The paper also discusses how human cognition is related to quality …
Mining Ontological Knowledge From Domain-Specific Text Documents, Xing Jiang, Ah-Hwee Tan
Mining Ontological Knowledge From Domain-Specific Text Documents, Xing Jiang, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
Traditional text mining systems employ shallow parsing techniques and focus on concept extraction and taxonomic relation extraction. This paper presents a novel system called CRCTOL for mining rich semantic knowledge in the form of ontology from domain-specific text documents. By using a full text parsing technique and incorporating both statistical and lexico-syntactic methods, the knowledge extracted by our system is more concise and contains a richer semantics compared with alternative systems. We conduct a case study wherein CRCTOL extracts ontological knowledge, specifically key concepts and semantic relations, from a terrorism domain text collection. Quantitative evaluation, by comparing with a state-of-the-art …
Nil Is Not Nothing: Recognition Of Chinese Network Informal Language Expressions, Yunqing Xia, Wong, Wei Gao, Wei Gao
Nil Is Not Nothing: Recognition Of Chinese Network Informal Language Expressions, Yunqing Xia, Wong, Wei Gao, Wei Gao
Research Collection School Of Computing and Information Systems
Informal language is actively used in network-mediated communication, e.g. chat room, BBS, email and text message. We refer the anomalous terms used in such context as network informal language (NIL) expressions. For example, “偶(ou3)” is used to replace “我(wo3)” in Chinese ICQ. Without unconventional resource, knowledge and techniques, the existing natural language processing approaches exhibit less effectiveness in dealing with NIL text. We propose to study NIL expressions with a NIL corpus and investigate techniques in processing NIL expressions. Two methods for Chinese NIL expression recognition are designed in NILER system. The experimental results show that pattern matching method produces …
Nil Is Not Nothing: Recognition Of Chinese Network Informal Language Expressions, Yunqing Xia, Kam-Fai Wong, Wei Gao
Nil Is Not Nothing: Recognition Of Chinese Network Informal Language Expressions, Yunqing Xia, Kam-Fai Wong, Wei Gao
Research Collection School Of Computing and Information Systems
Informal language is actively used in network-mediated communication, e.g. chat room, BBS, email and text message. We refer the anomalous terms used in such context as network informal language (NIL) expressions. For example, “(ou3)” is used to replace “ᚒ(wo3)” in Chinese ICQ. Without unconventional resource, knowledge and techniques, the existing natural language processing approaches exhibit less effectiveness in dealing with NIL text. We propose to study NIL expressions with a NIL corpus and investigate techniques in processing NIL expressions. Two methods for Chinese NIL expression recognition are designed in NILER system. The experimental results show that pattern matching method produces …
Cuhk At Imageclef 2005: Cross-Language And Cross-Media Image Retrieval, Steven C. H. Hoi, J. Zhu, M. Lyu
Cuhk At Imageclef 2005: Cross-Language And Cross-Media Image Retrieval, Steven C. H. Hoi, J. Zhu, M. Lyu
Research Collection School Of Computing and Information Systems
In this paper, we describe our studies of cross-language and cross-media image retrieval at the ImageCLEF 2005. This is the first participation of our CUHK (The Chinese University of Hong Kong) group at ImageCLEF. The task in which we participated is the “bilingual ad hoc retrieval” task. There are three major focuses and contributions in our participation. The first is the empirical evaluation of language models and smoothing strategies for cross-language image retrieval. The second is the evaluation of cross-media image retrieval, i.e., combining text and visual contents for image retrieval. The last is the evaluation of bilingual image retrieval …
A Semiotics View Of Modeling Method Complexity – The Case Of Uml, Keng Siau, Y. Tian
A Semiotics View Of Modeling Method Complexity – The Case Of Uml, Keng Siau, Y. Tian
Research Collection School Of Computing and Information Systems
Unified Modeling Language (UML) is the standard modeling language for object oriented system development. Despite its status as a standard, UML’s formal specification is fuzzy and its theoretical foundation is weak. Semiotics, the study of signs, provides us good theoretical foundation for UML research as UML graphical notations are some kinds of signs. In this research, we use semiotics to study the graphical notations in UML. We hypothesized that using iconic signs as UML graphical notations leads to more accurate representation and arouses fewer connotations than using symbolic signs. Since symbolic signs involve more learning efforts, we assume that expert …
On Assigning Place Names To Geography Related Web Pages, Wenbo Zong, Dan Wu, Aixin Sun, Ee Peng Lim, Dion Hoe-Lian Goh
On Assigning Place Names To Geography Related Web Pages, Wenbo Zong, Dan Wu, Aixin Sun, Ee Peng Lim, Dion Hoe-Lian Goh
Research Collection School Of Computing and Information Systems
In this paper, we attempt to give spatial semantics to web pages by assigning them place names. The entire assignment task is divided into three sub-problems, namely place name extraction, place name disambiguation and place name assignment. We propose our approaches to address these sub-problems. In particular, we have modified GATE, a well-known named entity extraction software, to perform place name extraction using a US Census gazetteer. A rule-based place name disambiguation method and a place name assignment method capable of assigning place names to web page segments have also been proposed. We have evaluated our proposed disambiguation and assignment …
Event-Driven Document Selection For Terrorism, Zhen Sun, Ee Peng Lim, Kuiyu Chang, Teng-Kwee Ong, Rohan Kumar Gunaratna
Event-Driven Document Selection For Terrorism, Zhen Sun, Ee Peng Lim, Kuiyu Chang, Teng-Kwee Ong, Rohan Kumar Gunaratna
Research Collection School Of Computing and Information Systems
In this paper, we examine the task of extracting information about terrorism related events hidden in a large document collection. The task assumes that a terrorism related event can be described by a set of entity and relation instances. To reduce the amount of time and efforts in extracting these event related instances, one should ideally perform the task on the relevant documents only. We have therefore proposed some document selection strategies based on information extraction (IE) patterns. Each strategy attempts to select one document at a time such that the gain of event related instance information is maximized. Our …
Video Summarization And Scene Detection By Graph Modeling, Chong-Wah Ngo, Yu-Fei Ma, Hong-Jiang Zhang
Video Summarization And Scene Detection By Graph Modeling, Chong-Wah Ngo, Yu-Fei Ma, Hong-Jiang Zhang
Research Collection School Of Computing and Information Systems
In this paper, we propose a unified approach for video summarization based on the analysis of video structures and video highlights. Two major components in our approach are scene modeling and highlight detection. Scene modeling is achieved by normalized cut algorithm and temporal graph analysis, while highlight detection is accomplished by motion attention modeling. In our proposed approach, a video is represented as a complete undirected graph and the normalized cut algorithm is carried out to globally and optimally partition the graph into video clusters. The resulting clusters form a directed temporal graph and a shortest path algorithm is proposed …
Automatic Model Structuring From Text Using Biomedical Ontology, Joshi R., Li X., Ramachandaran S., Tze-Yun Leong
Automatic Model Structuring From Text Using Biomedical Ontology, Joshi R., Li X., Ramachandaran S., Tze-Yun Leong
Research Collection School Of Computing and Information Systems
Bayesian Networks and Influence Diagrams are effective methods for structuring clinical problems. Constructing a relevant structure without the numerical probabilities in itself is a challenging task. In addition, due to the rapid rate of innovations and new findings in the biomedical domain, constructing a relevant graphical model becomes even more challenging. Building a model structure from text with minimum intervention from domain experts and minimum training examples has always been a challenge for the researchers. In the biomedical domain, numerous advances have been made which may make this dream a possibility now. We are currently trying to build a general …
Justilm: Few-Shot Justification Generation For Explainable Fact-Checking Of Real-World Claims, Fengzhu Zeng, Wei Gao
Justilm: Few-Shot Justification Generation For Explainable Fact-Checking Of Real-World Claims, Fengzhu Zeng, Wei Gao
Research Collection School Of Computing and Information Systems
Justification is an explanation that supports the verdict assigned to a claim in fact-checking. However, the task of justification generation is previously oversimplified as summarization of fact-check article authored by professional checkers. In this work, we propose a realistic approach to generate justification based on retrieved evidence. We present a new benchmark dataset called ExClaim for Explainable Claim verification, and introduce JustiLM, a novel few-shot retrieval-augmented language model to learn justification generation by leveraging fact-check articles as auxiliary resource during training. Our results show that JustiLM outperforms in-context learning (ICL)-enabled LMs including Flan-T5 and Llama2, and the retrieval-augmented model Atlas …
Improving Transliteration With Precise Alignment Of Phoneme Chunks And Using Contextual Features, Wei Gao, Kam-Fai Wong, Wai Lam
Improving Transliteration With Precise Alignment Of Phoneme Chunks And Using Contextual Features, Wei Gao, Kam-Fai Wong, Wai Lam
Research Collection School Of Computing and Information Systems
Automatic transliteration of foreign names is basically regarded as a diminutive clone of the machine translation (MT) problem. It thus follows IBM’s conventional MT models under the sourcechannel framework. Nonetheless, some parameters of this model dealing with zero-fertility words in the target sequences, can negatively impact transliteration effectiveness because of the inevitable inverted conditional probability estimation. Instead of source-channel, this paper presents a direct probabilistic transliteration model using contextual features of phonemes with a tailored alignment scheme for phoneme chunks. Experiments demonstrate superior performance over the source-channel for the task of English-Chinese transliteration.
A Spectroscopy Of Texts For Effective Clustering, Wenyuan Li, Wee-Keong Ng, Kok-Leong Ong, Ee Peng Lim
A Spectroscopy Of Texts For Effective Clustering, Wenyuan Li, Wee-Keong Ng, Kok-Leong Ong, Ee Peng Lim
Research Collection School Of Computing and Information Systems
For many clustering algorithms, such as k-means, EM, and CLOPE, there is usually a requirement to set some parameters. Often, these parameters directly or indirectly control the number of clusters to return. In the presence of different data characteristics and analysis contexts, it is often difficult for the user to estimate the number of clusters in the data set. This is especially true in text collections such as Web documents, images or biological data. The fundamental question this paper addresses is: ldquoHow can we effectively estimate the natural number of clusters in a given text collection?rdquo. We propose to use …
Phoneme-Based Transliteration Of Foreign Names For Oov Problem, Wei Gao, Kam-Fai Wong, Wai Lam
Phoneme-Based Transliteration Of Foreign Names For Oov Problem, Wei Gao, Kam-Fai Wong, Wai Lam
Research Collection School Of Computing and Information Systems
A proper noun dictionary is never complete rendering name translation from English to Chinese ineffective. One way to solve this problem is not to rely on a dictionary alone but to adopt automatic translation according to pronunciation similarities, i.e. to map phonemes comprising an English name to the phonetic representations of the corresponding Chinese name. This process is called transliteration. We present a statistical transliteration method. An efficient algorithm for aligning phoneme chunks is described. Unlike rule-based approaches, our method is data-driven. Compared to source-channel based statistical approaches, we adopt a direct transliteration model, i.e. the direction of probabilistic estimation …
Predicting Nonlinear Network Traffic Using Fuzzy Neural Network, Zhaoxia Wang, Tingzhu Hao, Zengqiang Chen, Zhuzhi Yuan
Predicting Nonlinear Network Traffic Using Fuzzy Neural Network, Zhaoxia Wang, Tingzhu Hao, Zengqiang Chen, Zhuzhi Yuan
Research Collection School Of Computing and Information Systems
Network traffic is a complex and nonlinear process, which is significantly affected by immeasurable parameters and variables. This paper addresses the use of the five-layer fuzzy neural network (FNN) for predicting the nonlinear network traffic. The structure of this system is introduced in detail. Through training the FNN using back-propagation algorithm with inertia] terms the traffic series can be well predicted by this FNN system. We analyze the performance of the FNN in terms of prediction ability as compared with solely neural network. The simulation demonstrates that the proposed FNN is superior to the solely neural network systems. In addition, …
Automatic Video Summarization By Graph Modeling, Chong-Wah Ngo, Yu-Fei Ma, Hong-Jiang Zhang
Automatic Video Summarization By Graph Modeling, Chong-Wah Ngo, Yu-Fei Ma, Hong-Jiang Zhang
Research Collection School Of Computing and Information Systems
We propose a unified approach for summarization based on the analysis of video structures and video highlights. Our approach emphasizes both the content balance and perceptual quality of a summary. Normalized cut algorithm is employed to globally and optimally partition a video into clusters. A motion attention model based on human perception is employed to compute the perceptual quality of shots and clusters. The clusters, together with the computed attention values, form a temporal graph similar to Markov chain that inherently describes the evolution and perceptual importance of video clusters. In our application, the flow of a temporal graph is …
Aggregated Causal Maps: An Approach To Elicit And Aggregate The Knowledge Of Multiple Experts, S. Nadkarni, Fiona Fui-Hoon Nah
Aggregated Causal Maps: An Approach To Elicit And Aggregate The Knowledge Of Multiple Experts, S. Nadkarni, Fiona Fui-Hoon Nah
Research Collection School Of Computing and Information Systems
This paper presents a systematic procedure to elicit and aggregate the knowledge of multiple individual experts and represent it in the form of an Aggregated Causal Map (ACM). This procedure differs from existing methods in two ways. First, unlike other methods, this method does not rely on group interaction in eliciting knowledge of multiple experts, and, therefore, is not fraught with biases associated with group dynamics. Second, this method uses both the idiographic and nomothetic approaches while existing methods focus on nomothetic approaches to knowledge elicitation. We draw on the strengths of both approaches by using the idiographic approach to …
The Effect Of Domain Knowledge On Icon Visualization, Keng Siau, Fiona Fui-Hoon Nah
The Effect Of Domain Knowledge On Icon Visualization, Keng Siau, Fiona Fui-Hoon Nah
Research Collection School Of Computing and Information Systems
Iconic interfaces are now the de facto interface for most computer systems. Despite the popularity of iconic interfaces and the widespread belief that iconic interfaces are easier to comprehend than non-iconic interfaces, we have not come across any published study that has examined the effect of domain knowledge on end users’ interpretation of icons. An understanding of the relationship between domain knowledge and its effect on interpretation will enable us to design better icons to not only facilitate end users’ interpretation but also reduce misinterpretations of icons. This paper reports on an experimental study that investigates the effect of domain …
Using Support Vector Machines For Terrorism Information Extraction, Aixin Sun, Myo-Myo Naing, Ee Peng Lim, Wai Lam
Using Support Vector Machines For Terrorism Information Extraction, Aixin Sun, Myo-Myo Naing, Ee Peng Lim, Wai Lam
Research Collection School Of Computing and Information Systems
Information extraction (IE) is of great importance in many applications including web intelligence, search engines, text understanding, etc. To extract information from text documents, most IE systems rely on a set of extraction patterns. Each extraction pattern is defined based on the syntactic and/or semantic constraints on the positions of desired entities within natural language sentences. The IE systems also provide a set of pattern templates that determines the kind of syntactic and semantic constraints to be considered. In this paper, we argue that such pattern templates restricts the kind of extraction patterns that can be learned by IE systems. …
Guest Editorial: Text And Web Mining, Ah-Hwee Tan, Philip S. Yu
Guest Editorial: Text And Web Mining, Ah-Hwee Tan, Philip S. Yu
Research Collection School Of Computing and Information Systems
Text mining and web mining are two interrelated fields that have received a lot of attention in recent years. Text mining [1, 2] is concerned with the analysis of very large document collections and the extraction of hidden knowledge from text-based data. Web mining [3] refers to the analysis and mining of all web-related data, including web content, hyperlink structure, and web access statistics.
A Typology For Understanding The Role Of Information As A Source Of Value Creation In The Emerging Information Economy, J. Mcintosh, Keng Siau
A Typology For Understanding The Role Of Information As A Source Of Value Creation In The Emerging Information Economy, J. Mcintosh, Keng Siau
Research Collection School Of Computing and Information Systems
Today’s economy is increasingly driven by the integration of information in many aspects of business. Greater information intensity in industries such as hospital supply and express package delivery is causing a fundamental transformation in the way firms conduct business, the menu of competitive choices that they are faced with, and the need to continuously keep ahead of competitors. Information driven businesses appear to adopt several competitive or operating innovations. These include: mass customization or the creation of customized products which offer virtually individualized products to customers in mass markets (Pine, 1993); disintermediation or the creation of direct links between producers …
Theoretical Foundation For Relationship Construct In Information Modeling – Relation Element Theory, Keng Siau
Theoretical Foundation For Relationship Construct In Information Modeling – Relation Element Theory, Keng Siau
Research Collection School Of Computing and Information Systems
Information modeling is a critical process in software development. One of the key constructs in information modeling is the relationship construct. Though commonly used, the relationship construct is poorly defined and lacks a strong theoretical foundation. The objectives of this research are to define and classify the various relationships based on a theory in linguistic known as the relation element theory. This paper describes the theory, relates the theory to the relationship construct, and discusses the implication of the theory on the relationship construct.
Export Database Derivation Approach For Supporting Object-Oriented Wrapper Queries, Ee Peng Lim, Hon-Kuan Lee
Export Database Derivation Approach For Supporting Object-Oriented Wrapper Queries, Ee Peng Lim, Hon-Kuan Lee
Research Collection School Of Computing and Information Systems
Wrappers export the schema and data of existing heterogeneous databases and support queries on them. In the context of cooperative information systems, we present a flexible approach to specify the derivation of object-oriented (OO) export databases from local relational databases. Our export database derivation consists of a set of extent derivation structures (EDS) which defines the extent and deep extent of export classes. Having well-defined semantics, the EDS can be readily used in transforming wrapper queries to local queries. Based on the EDS, we developed a wrapper query evaluation strategy which handles OO queries on the export databases. The strategy …
Identifying Faces Using Multiple Retrievals, Jian Kang Wu, Arcot Desai Narasimhalu
Identifying Faces Using Multiple Retrievals, Jian Kang Wu, Arcot Desai Narasimhalu
Research Collection School Of Computing and Information Systems
During a police investigation, officers often have to sort through hundreds of photographs to identify a suspect. To aid this task, we at the Institute of Systems Science developed and implemented a flexible database system that can retrieve faces using personal information, fuzzy and free-text descriptors, and classification trees.