Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (7282)
- Computer Sciences (7169)
- Databases and Information Systems (2934)
- Software Engineering (2227)
- Social and Behavioral Sciences (2167)
-
- Business (1886)
- Artificial Intelligence and Robotics (1367)
- Engineering (1103)
- Numerical Analysis and Scientific Computing (864)
- International and Area Studies (852)
- Asian Studies (835)
- Information Security (740)
- Graphics and Human Computer Interfaces (642)
- Computer Engineering (548)
- Public Affairs, Public Policy and Public Administration (460)
- Operations Research, Systems Engineering and Industrial Engineering (451)
- Law (410)
- Theory and Algorithms (397)
- Technology and Innovation (380)
- Programming Languages and Compilers (360)
- Education (348)
- Communication (311)
- Economics (307)
- OS and Networks (272)
- Finance and Financial Management (242)
- Organizational Behavior and Theory (239)
- Strategic Management Policy (237)
- Higher Education (226)
- Social Media (221)
- Transportation (215)
- Keyword
-
- Singapore (284)
- Machine learning (131)
- Deep learning (118)
- Artificial intelligence (96)
- Innovation (82)
-
- Social media (79)
- Singapore Management University (77)
- China (70)
- Data mining (66)
- Reinforcement learning (59)
- Empirical study (57)
- Higher education (55)
- Software engineering (55)
- Privacy (52)
- Security (51)
- Deep Learning (50)
- Cloud computing (48)
- Online learning (48)
- Collaboration (47)
- Optimization (47)
- Training (47)
- Twitter (47)
- Task analysis (46)
- Neural networks (45)
- Sustainability (45)
- Visualization (45)
- COVID-19 (44)
- Natural language processing (44)
- Anomaly detection (43)
- Feature extraction (42)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (7017)
- Research Collection Lee Kong Chian School Of Business (838)
- Research Collection Yong Pung How School Of Law (354)
- Research Collection School of Social Sciences (331)
- Dissertations and Theses Collection (Open Access) (325)
-
- Research Collection College of Integrative Studies (221)
- Research Collection School Of Economics (189)
- Perspectives@SMU (116)
- Asian Management Insights (113)
- Research Collection School Of Accountancy (98)
- Knowledge@SMU (79)
- Research Collection Library (69)
- SMU Press Releases and News (38)
- Social Space (34)
- Oral History Collection (22)
- Dissertations and Theses Collection (17)
- Report to Stakeholders (16)
- Sim Kee Boon Institute for Financial Economics (16)
- CCX Research (14)
- Research@SMU: Connecting the Dots (11)
- MITB Thought Leadership Series (9)
- SMU Corporate Reports (9)
- Singapore Law Journal (Lexicon) (9)
- Student Publications (8)
- FORCE 2026 (7)
- Research Collection Institute of Innovation and Entrepreneurship (7)
- Centre for AI & Data Governance (2019-2025) (6)
- Research Collection Institute of Service Excellence (2007-2024) (6)
- Research Collection Office of Impact (6)
- COAR Asia OA Meeting 2021 (5)
- Publication Type
- File Type
Articles 8731 - 8760 of 10054
Full-Text Articles in Entire DC Network
Harmoni: Context-Aware Filtering Of Sensor Data For Continuous Remote Health Monitoring, Iqbal Mohomed, Archan Misra, Maria Ebling, William Jerome
Harmoni: Context-Aware Filtering Of Sensor Data For Continuous Remote Health Monitoring, Iqbal Mohomed, Archan Misra, Maria Ebling, William Jerome
Research Collection School Of Computing and Information Systems
A promising architecture for remote healthcare monitoring involves the use of a pervasive device (such as a cellular phone), which aggregates data from multiple body-worn medical sensors and transmits the data to the backend. Unfortunately, the volume of data generated by increasingly sophisticated continuouslyactive sensors can overwhelm the resources on the mobile device. We propose imbuing the mobile device with the intelligence to perform context-aware filtering of sensor data streams in order to reduce transmissions in cases where the observed data corresponds to the norm expected by the system in a given context. To investigate the efficacy of this technique, …
How Friendly Is Too Friendly?, M. Thulasidas
How Friendly Is Too Friendly?, M. Thulasidas
Research Collection School Of Computing and Information Systems
Being a boss is tough and being a good boss is a tricky balancing act. One issue many bosses face is: How friendly can they become with their team?
Target Saving In An Overlapping Generations Model, Brishti Guha, Ashok S. Guha
Target Saving In An Overlapping Generations Model, Brishti Guha, Ashok S. Guha
Research Collection School Of Economics
We examine a model in which the utility function has been engineered so that it is optimal for consumers to aim for a fixed target level of retirement resources. In this case, consumption displays excess sensitivity to current income as well as perfect old age insurance. In an overlapping generations model, this leads naturally to multiple and unstable equilibria. Under static expectations, it also leads to a well-defined dynamics, including possible historical traps, implosions involving ever-diminishing capital stock and ever-increasing interest rates, and the feasibility of optimal one-time interventions.
On-Line Discovery Of Hot Motion Paths, Dimitris Sacharidis, Kostas Patroumpas, Manolis Terrovitis, Verena Kantere, Michalis Potamias, Kyriakos Mouratidis, Timos Sellis
On-Line Discovery Of Hot Motion Paths, Dimitris Sacharidis, Kostas Patroumpas, Manolis Terrovitis, Verena Kantere, Michalis Potamias, Kyriakos Mouratidis, Timos Sellis
Research Collection School Of Computing and Information Systems
We consider an environment of numerous moving objects, equipped with location-sensing devices and capable of communicating with a central coordinator. In this setting, we investigate the problem of maintaining hot motion paths, i.e., routes frequently followed by multiple objects over the recent past. Motion paths approximate portions of objects' movement within a tolerance margin that depends on the uncertainty inherent in positional measurements. Discovery of hot motion paths is important to applications requiring classification/profiling based on monitored movement patterns, such as targeted advertising, resource allocation, etc. To achieve this goal, we delegate part of the path extraction process to objects, …
Processing Transitive Nearest-Neighbor Queries In Multi-Channel Access Environments, Xiao Zhang, Wang-Chien Lee, Prasnjit Mitra, Baihua Zheng
Processing Transitive Nearest-Neighbor Queries In Multi-Channel Access Environments, Xiao Zhang, Wang-Chien Lee, Prasnjit Mitra, Baihua Zheng
Research Collection School Of Computing and Information Systems
Wireless broadcast is an efficient way for information dissemination due to its good scalability [10]. Existing works typically assume mobile devices, such as cell phones and PDAs, can access only one channel at a time. In this paper, we consider a scenario of near future where a mobile device has the ability to process queries using information simultaneously received from multiple channels. We focus on the query processing of the transitive nearest neighbor (TNN) search [19]. Two TNN algorithms developed for a single broadcast channel environment are adapted to our new broadcast enviroment. Based on the obtained insights, we propose …
R&D Project Scheduling When Activities May Fail, Bert De Reyck, Roel Leus
R&D Project Scheduling When Activities May Fail, Bert De Reyck, Roel Leus
Research Collection Lee Kong Chian School Of Business
An R&D project typically consists of several stages. Due to technological risks, the project may have to be terminated before completion, each stage having a specific likelihood of success. In the project planning and scheduling literature, this technological uncertainty has typically been ignored and project plans are developed only for scenarios in which the project succeeds. In this paper we examine how to schedule projects in order to maximize their expected net present value when the project activities have a probability of failure and when an activity's failure leads to overall project termination. We formulate the problem, show that it …
Multimodal News Story Clustering With Pairwise Visual Near-Duplicate Constraint, Xiao Wu, Chong-Wah Ngo, Alexander G. Hauptmann
Multimodal News Story Clustering With Pairwise Visual Near-Duplicate Constraint, Xiao Wu, Chong-Wah Ngo, Alexander G. Hauptmann
Research Collection School Of Computing and Information Systems
Story clustering is a critical step for news retrieval, topic mining, and summarization. Nonetheless, the task remains highly challenging owing to the fact that news topics exhibit clusters of varying densities, shapes, and sizes. Traditional algorithms are found to be ineffective in mining these types of clusters. This paper offers a new perspective by exploring the pairwise visual cues deriving from near-duplicate keyframes (NDK) for constraint-based clustering. We propose a constraint-driven co-clustering algorithm (CCC), which utilizes the near-duplicate constraints built on top of text, to mine topic-related stories and the outliers. With CCC, the duality between stories and their underlying …
Integrating Temporal Difference Methods And Self‐Organizing Neural Networks For Reinforcement Learning With Delayed Evaluative Feedback, Ah-Hwee Tan, Ning Lu, Dan Xiao
Integrating Temporal Difference Methods And Self‐Organizing Neural Networks For Reinforcement Learning With Delayed Evaluative Feedback, Ah-Hwee Tan, Ning Lu, Dan Xiao
Research Collection School Of Computing and Information Systems
This paper presents a neural architecture for learning category nodes encoding mappings across multimodal patterns involving sensory inputs, actions, and rewards. By integrating adaptive resonance theory (ART) and temporal difference (TD) methods, the proposed neural model, called TD fusion architecture for learning, cognition, and navigation (TD-FALCON), enables an autonomous agent to adapt and function in a dynamic environment with immediate as well as delayed evaluative feedback (reinforcement) signals. TD-FALCON learns the value functions of the state-action space estimated through on-policy and off-policy TD learning methods, specifically state-action-reward-state-action (SARSA) and Q-learning. The learned value functions are then used to determine the …
On Ranking Controversies In Wikipedia: Models And Evaluation, Ba-Quy Vuong, Ee Peng Lim, Aixin Sun, Minh-Tam Le, Hady Wirawan Lauw, Kuiyu Chang
On Ranking Controversies In Wikipedia: Models And Evaluation, Ba-Quy Vuong, Ee Peng Lim, Aixin Sun, Minh-Tam Le, Hady Wirawan Lauw, Kuiyu Chang
Research Collection School Of Computing and Information Systems
Wikipedia 1 is a very large and successful Web 2.0 example. As the number of Wikipedia articles and contributors grows at a very fast pace, there are also increasing disputes occurring among the contributors. Disputes often happen in articles with controversial content. They also occur frequently among contributors who are "aggressive" or controversial in their personalities. In this paper, we aim to identify controversial articles in Wikipedia. We propose three models, namely the Basic model and two Controversy Rank (CR) models. These models draw clues from collaboration and edit history instead of interpreting the actual articles or edited content. While …
Wafer-Bonded Active/Passive Vertically Coupled Microring Lasers, M. Hamacher, H. Heidrich, U. Troppenz, D. Syvridis, D. Alexandropoulos, S. Mikroulis, A. Kapsalis, Chyng Wen Tee, K. A. Williams, V. Dragoi, M. Alexe, D. Cristea, M. Kusko
Wafer-Bonded Active/Passive Vertically Coupled Microring Lasers, M. Hamacher, H. Heidrich, U. Troppenz, D. Syvridis, D. Alexandropoulos, S. Mikroulis, A. Kapsalis, Chyng Wen Tee, K. A. Williams, V. Dragoi, M. Alexe, D. Cristea, M. Kusko
Research Collection Lee Kong Chian School Of Business
We summarize the results of a European Project entitled WAPITI (Waferbonding and Active Passive Integration Technology and Implementation) dealing with the fabrication and investigation of active/passive vertically coupled ring resonators, wafer bonded on GaAs, and based on full wafer technology. The concept allows for the integration of an active ring laser vertically coupled to a transparent bus waveguide. All necessary layers are grown in a single epitaxial run so that the critical coupling gap can be precisely controlled with the high degree of accuracy of epitaxial growth. One key challenge of the project …
The Dilemmas Of Giving: The Heart Of Paradox, Charles Hampden-Turner, Teng Kee Tan
The Dilemmas Of Giving: The Heart Of Paradox, Charles Hampden-Turner, Teng Kee Tan
Social Space
In their attempts to ‘do-good’ and alleviate the pains of the less fortunate, the impoverished and the disadvantaged, foundations and charitable bodies face common dilemmas. Professor Charles Hampden-Turner and Professor Tan Teng Kee explore.
Overseas Giving: Should Charity Begin At Home?, Chi Chiu Tan
Overseas Giving: Should Charity Begin At Home?, Chi Chiu Tan
Social Space
In extending a hand overseas with developmental and humanitarian aid, is Singapore doing what is best for itself and the recipient communities? And what role does its government have to play in this arena? Dr Tan Chi Chiu weighs in.
After The Tigers: Building A Competitive Citizen Sector, Chris Cusano
After The Tigers: Building A Competitive Citizen Sector, Chris Cusano
Social Space
The citizen sector is a new, yet fundamental idea that underpins the modern phenomenon of social entrepreneurship. Chris Cusano describes how the sector is taking shape and the challenges it faces.
Firm Diversification And Earnings Management: Evidence From Seasoned Equity Offerings, Chee Yeow Lim, Tiong Yang Thong, David K. Ding
Firm Diversification And Earnings Management: Evidence From Seasoned Equity Offerings, Chee Yeow Lim, Tiong Yang Thong, David K. Ding
Research Collection Lee Kong Chian School Of Business
Popular press suggests that diversified firms are more aggressive in managing earnings than non-diversified firms. We examine this claim in the seasoned equity offering (SEO) setting, where firms have been shown to have the incentive to manage earnings upwards. Using the cross-sectional modified Jones [(1991) J Accounting Res 29:193–228] model to measure discretionary current accruals, we find that discretionary current accruals are higher among diversified firms than in non-diversified ones. Our evidence is consistent with the view that the extent of firm diversification is directly related to the degree of earnings management. We further show that diversified issuers with high …
Technological Change Management Strategies In Asian Small-Scale Businesses: Trends In Singapore, Thomas Menkhoff, Yue Wah Chay
Technological Change Management Strategies In Asian Small-Scale Businesses: Trends In Singapore, Thomas Menkhoff, Yue Wah Chay
Research Collection Lee Kong Chian School Of Business
Based on survey data on the change management behavior of Chinese small and medium sized enterprises (SMEs) in Singapore, the paper explores how small entrepreneurs are coping with the city-state's turbulent business environment, processes of technological advancement and accelerated change. Differences between so-called opportunistic entrepreneurs and small business ventures are examined. Conceptually, the paper is informed by theories of change management, strategic choice, entrepreneurship and Chinese business. Special emphasis is put on the identification of demographic characteristics of "technological change masters" in Singapore's small business sector so as to gain an understanding of both the dynamism and relative passivity of …
Interviewers' Sensitivity To Impression Management Tactics In Structured Interviews, Filip Lievens, Helga Peeters
Interviewers' Sensitivity To Impression Management Tactics In Structured Interviews, Filip Lievens, Helga Peeters
Research Collection Lee Kong Chian School Of Business
This study examines interviewers' sensitivity to impression management in structured interviews by determining the relative importance that interviewers attach to ( verbal and nonverbal) impression management as compared to the relative importance that they attach to predetermined competencies. Two samples of interviewers ( 55 Master I/O psychology students and 18 professional interviewers) watched and evaluated videotaped interviewees who were instructed to put their best foot forward. Results of relative weight analyses showed that the importance of verbal and nonverbal impression management tactics was relatively small as compared to the importance attached to job-related competencies. The type of interview format had …
Technology Strategy And China's Technology Capacity Building, Arnoud De Meyer
Technology Strategy And China's Technology Capacity Building, Arnoud De Meyer
Research Collection Lee Kong Chian School Of Business
China has the potential to become a major source of innovation for the world. The scientific investment is in place and rapidly growing. But in order to reap the benefits of this investment its organisations will have to become better at managing innovation. One of the key elements of innovation management is the determination and implementation of a sound technology strategy. The purpose of this paper is to offer a framework and a detailed overview of what it entails to develop and implement a technology strategy. The paper emphasizes the alignment of the strategy with the organisational competencies and the …
Multi-Echelon Repairable Item Inventory System With Limited Repair Capacity Under Nonstationary Demands, Hoong Chuin Lau, Huawei Song
Multi-Echelon Repairable Item Inventory System With Limited Repair Capacity Under Nonstationary Demands, Hoong Chuin Lau, Huawei Song
Research Collection School Of Computing and Information Systems
Classical multi-echelon repairable item inventory models are based either on steady-state analysis or infinite repair capacity, which may not work well in situations when the demand is nonstationary, or repair capacity is limited. In this paper, we propose an analytical model for evaluating system performance that works well under limited repair capacity and nonstationary demands. Following the METRIC methodology, we then develop an optimisation algorithm to solve the corrective maintenance problem in military logistics. Experimental results show that our approach yields good solutions efficiently. This work has also resulted in a software that has been field-tested by a military organisation.
Enhancing Recursive Supervised Learning Using Clustering And Combinatorial Optimization (Rsl-Cc), Kiruthika Ramanathan, Sheng Uei Guan
Enhancing Recursive Supervised Learning Using Clustering And Combinatorial Optimization (Rsl-Cc), Kiruthika Ramanathan, Sheng Uei Guan
Research Collection School Of Computing and Information Systems
The use of a team of weak learners to learn a dataset has been shown better than the use of one single strong learner. In fact, the idea is so successful that boosting, an algorithm combining several weak learners for supervised learning, has been considered to be one of the best off-the-shelf classifiers. However, some problems still remain, including determining the optimal number of weak learners and the overfitting of data. In an earlier work, we developed the RPHP algorithm which solves both these problems by using a combination of genetic algorithm, weak learner and pattern distributor. In this paper, …
Face Annotation Using Transductive Kernel Fisher Discriminant, Jianke Zhu, Steven C. H. Hoi, Michael R. Lyu
Face Annotation Using Transductive Kernel Fisher Discriminant, Jianke Zhu, Steven C. H. Hoi, Michael R. Lyu
Research Collection School Of Computing and Information Systems
Face annotation in images and videos enjoys many potential applications in multimedia information retrieval. Face annotation usually requires many training data labeled by hand in order to build effective classifiers. This is particularly challenging when annotating faces on large-scale collections of media data, in which huge labeling efforts would be very expensive. As a result, traditional supervised face annotation methods often suffer from insufficient training data. To attack this challenge, in this paper, we propose a novel Transductive Kernel Fisher Discriminant (TKFD) scheme for face annotation, which outperforms traditional supervised annotation methods with few training data. The main idea of …
Factors Affecting The Information Quality Of Personal Web Portfolios, P. Katerattanakul, Keng Siau
Factors Affecting The Information Quality Of Personal Web Portfolios, P. Katerattanakul, Keng Siau
Research Collection School Of Computing and Information Systems
Personal Web portfolios have become a popular information source and an effective method for individuals to present themselves to others in cyberspace. Thus, the quality of personal Web portfolios is critical and affects the perception that others have of the individuals. But how do we measure quality of personal Web portfolios? What are the important factors affecting quality of personal Web portfolios? This study presents the development of an instrument measuring factors affecting information quality of personal Web portfolios. The proposed instrument, based on the Information Quality framework, was refined and validated to assess its construct validity, convergent validity, and …
Target Saving In An Overlapping Generations Model, Ashok S. Guha, Brishti Guha
Target Saving In An Overlapping Generations Model, Ashok S. Guha, Brishti Guha
Research Collection School Of Economics
We examine a model in which the utility function has been engineered so that it is optimal for consumers to aim for a fixed target level of retirement resources. In this case consumption displays excess sensitivity to current income as well as perfect old age insurance. In an overlapping generations model, this leads naturally to multiple and unstable equilibria. Under static expectations, it also leads to a well-defined dynamics, including possible historical traps, implosions involving ever-diminishing capital stock and ever-increasing interest rates, and the feasibility of optimal one-time interventions.
Education And Trade, Pao Li Chang, Fali Huang
Education And Trade, Pao Li Chang, Fali Huang
Research Collection School Of Economics
This paper examines the inherent link between a countryís education system and its comparative advantage in trade. It suggests that di§erences in education systems across countries are probably a stable equilibrium result that is compatible with and reinforced by trade patterns. In equilibrium, two distinct types of countries emerge, one that exports creativity-intensive products and has an education system encouraging diversity (as illustrated by the US), and the other one that exports high-quality manufactured products and has an education system promoting homogeneity in student quality (as illustrated by Japan). Our Öndings present a novel explanation for the coexistence of low …
Refined Inference On Long Memory In Realized Volatility, Peter C. B. Phillips, Offer Lieberman
Refined Inference On Long Memory In Realized Volatility, Peter C. B. Phillips, Offer Lieberman
Research Collection School Of Economics
There is an emerging consensus in empirical finance that realized volatility series typically display long range dependence with a memory parameter around 0.4 (Andersen et al., 2001; Martens et al., 2004). The present article provides some illustrative analysis of how long memory may arise from the accumulative process underlying realized volatility. The article also uses results in Lieberman and Phillips (2004, 2005) to refine statistical inference about by higher order theory. Standard asymptotic theory has an error rate for error rejection probabilities, and the theory used here refines the approximation to an error rate of. The new formula is independent …
The Asean Charter As "Legs To Go Places": Ideational Norms And Pragmatic Legalism In Community Building In Southeast Asia, Eugene K. B. Tan
The Asean Charter As "Legs To Go Places": Ideational Norms And Pragmatic Legalism In Community Building In Southeast Asia, Eugene K. B. Tan
Research Collection Yong Pung How School Of Law
The Charter of the Association of Southeast Asian Nations (ASEAN) has been hailed as a legal instrument that would integrate the ten constituent members as a community and a regional organization. Ostensibly, the Charter has three strategic thrusts in support of the vision of the ASEAN Community. The first is to formalize ASEAN as an institution while streamlining its decision-making processes. Secondly, the Charter seeks to strengthen ASEAN institutions. Thirdly, it seeks to establish mechanisms to monitor compliance and settle disputes. The article considers the extent to which the Charter will help ASEAN achieve its aims. This is especially pertinent …
Civil Liabilities For False Or Misleading Statements Made By Listed Companies To The Securities Markets In Singapore, Wai Yee Wan
Civil Liabilities For False Or Misleading Statements Made By Listed Companies To The Securities Markets In Singapore, Wai Yee Wan
Research Collection Yong Pung How School Of Law
This article examines the scope and efficacy of the civil remedies available to investors against listed companies which have made false or misleading statements in the secondary securities market in Singapore, both at common law and the statutory compensation scheme under the Securities and Futures Act. It argues that there are a number of limitations faced by such investors in bringing claims founded in tort law against the listed companies. While the statutory compensation scheme attempts to improve the position of investors, there are a number of deficiencies in the scheme the most significant of which is the ceiling on …
Pre-Commencement Discovery And The Odex Litigation: Copyright Versus Confidentiality Or Is It Privacy?, Sze Shun, George Wei
Pre-Commencement Discovery And The Odex Litigation: Copyright Versus Confidentiality Or Is It Privacy?, Sze Shun, George Wei
Research Collection Yong Pung How School Of Law
This article examines whether internet service providers are under any duty to disclose the names of subscribers whose accounts can be shown to be associated with infringing activity. This question involves tension between the economic interests of copyright owners/licensees, the privacy interests of internet users and the economic interests of the internet service provider. This tension in turn raises age-old problems of balance and proportionality between privacy, confidentiality and other competing rights and freedoms as well as the interests of society at large. The article concludes by briefly touching on privacy areas from outside of copyright and the Internet: including …
Columbia University/Vireo-Cityu/Irit Trecvid2008 High-Level Feature Extraction And Interactive Video Search, Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky
Columbia University/Vireo-Cityu/Irit Trecvid2008 High-Level Feature Extraction And Interactive Video Search, Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky
Research Collection School Of Computing and Information Systems
In this report, we present overview and comparative analysis of our HLF detection system, which achieves the top performance among all type-A submissions in 2008. We also describe preliminary evaluation of our video search system, CuZero, in the interactive search task.
Concept Detection: Convergence To Local Features And Opportunities Beyond, Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky
Concept Detection: Convergence To Local Features And Opportunities Beyond, Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky
Research Collection School Of Computing and Information Systems
No abstract provided.
Document Selection For Extracting Entity And Relationship Instances Of Terrorist Events, Zhen Sun, Ee Peng Lim, Kuiyu Chang, Maggy Anastasia Suryanto, Rohan Kumar Gunaratna
Document Selection For Extracting Entity And Relationship Instances Of Terrorist Events, Zhen Sun, Ee Peng Lim, Kuiyu Chang, Maggy Anastasia Suryanto, Rohan Kumar Gunaratna
Research Collection School Of Computing and Information Systems
In this chapter, we study the problem of selecting documents so as to extract terrorist event information from a collection of documents. We represent an event by its entity and relation instances. Very often, these entity and relation instances have to be extracted from multiple documents. We therefore define an information extraction (IE) task as selecting documents and extracting from which entity and relation instances relevant to a user-specified event (aka domain specific event entity and relation extraction). We adopt domain specific IE patterns to extract potentially relevant entity and relation instances from documents, and develop a number of document …