Anh Tuan Luu lists you as their PhD advisor. Claim this profile to confirm it and keep the rest of your record right.
Claim this profileAcademic lineage
View as a treeStudents and postdocs9
- Anran HaoFrom a thesis record ↗
- Thong T. NguyenFrom a thesis record ↗
- Yi TayFrom a thesis record ↗
- From a thesis record ↗
- Peng TangFrom a thesis record ↗
- Minh Luan NguyenFrom a thesis record ↗
- Thanh Tam NguyenFrom a thesis record ↗
- Baoyao ZhouFrom a thesis record ↗
Show 1 more
- Tien Dung DoFrom a thesis record ↗
Works161 from public data
- Collecting and Analyzing Multidimensional Data with Local Differential Privacy409
Novel LDP mechanisms for collecting a numeric attribute, whose accuracy is at least no worse (and usually better) than existing solutions in terms of worst-case noise variance are proposed, and extended to multidimensional data that can contain both numeric and categorical attributes, where they always outperform existing solutions regarding worst- case noise variance.
- Translational Recommender Networks.324
Qualitative studies demonstrate evidence that the proposed model is able to infer and encode explicit sentiment, temporal and attribute information despite being only trained on implicit feedback, ascertains the ability of LRML to uncover hidden relational structure within implicit datasets.
- Reasoning with Sarcasm by Reading In-Between212
This paper proposes an attention-based neural model that looks in-between instead of across, enabling it to explicitly model contrast and incongruity and achieves state-of-the-art performance on all datasets but also enjoys improved interpretability.
- Learning to Attend via Word-Aspect Associative Fusion for Aspect-Based Sentiment Analysis206
This paper proposes a novel method for integrating aspect information into the neural model by modeling word-aspect relationships and achieves state-of-the-art performance on benchmark datasets, outperforming ATAE-LSTM by 4%-5% on average across multiple datasets.
- 162
- SkipFlow: Incorporating Neural Coherence Features for End-to-End Automatic Text Scoring149
A new neural architecture that enhances vanilla neural network models with auxiliary neural coherence features with state-of-the-art performance on the benchmark ASAP dataset, outperforming not only feature engineering baselines but also other deep learning models.
- Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives126
A curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty, and a new Introspective Alignment Layer (IAL), which reasons over decomposed alignments using block-based self-attention.
- Facial expression recognition from line-based caricatures122
This work has proven the proposed idea that facial expressions can be characterized and recognized by caricatures and is thus suitable for real-time applications.
- Dyadic Memory Networks for Aspect-based Sentiment Analysis120
This paper proposes Dyadic Memory Networks (DyMemNN), a novel extension of end-to-end memory networks for aspect-based sentiment analysis (ABSA) that achieves the state-of-the-art performance and outperform many neural architectures across six benchmark datasets.
- Mining a Web Citation Database for author co-citation analysis110
A mining process to automate the ACA based on the Web Citation Database is proposed, which uses agglomerative hierarchical clustering (AHC) as the mining technique for author clustering and multidimensional scaling (MDS) for displaying author cluster maps.
- Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference102
A new architecture where alignment pairs are compared, compressed and then propagated to upper layers for enhanced representation learning is introduced, and factorization layers are adopted for efficient and expressive compression of alignment vectors into scalar features, which are then used to augment the base word representations.
- Automatic summary assessment for intelligent tutoring systems89
An ensemble approach that integrates LSA and n-gram co-occurrence is proposed that is able to achieve high accuracy and improve the performance quite substantially compared with current techniques.
- Automatic Generation of Ontology for Scholarly Semantic Web80
This paper proposes to incorporate fuzzy logic into FCA for automatic generation of ontology, and discusses the Scholarly Semantic Web, and the ontology generation process from the FFCA framework.
- Learning Term Embeddings for Taxonomic Relation Identification Using Dynamic Weighting Neural Network77
A novel supervised learning approach for identifying taxonomic relations using term embeddings that out-performs other state-of-the-art methods by 9% to 13% in terms of accuracy for both general and specific domain datasets.
- A Fuzzy FCA-based Approach to Conceptual Clustering for Automatic Generation of Concept Hierarchy on Uncertainty Data76
This paper proposes a new fuzzy FCA-based approach to conceptual clustering for automatic generation of concept hierarchy on uncertainty data and applies the proposed approach to generate a concept hierarchy of research areas from a citation database.
- Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks72
This paper proposes a series of lightweight and memory efficient neural architectures for a potpourri of natural language processing (NLP) tasks, exploiting computation using Quaternion algebra and hypercomplex spaces, enabling not only expressive inter-component interactions but also significantly reduced parameter size due to lesser degrees of freedom in the Hamilton product.
- A Compare-Propagate Architecture with Alignment Factorization for Natural Language Inference71
A new compare-propagate architecture is introduced where alignments pairs are compared and then propagated to upper layers for enhanced representation learning, and novel factorization layers are adopted for efficient compression of alignment vectors into scalar valued features, which are then used to augment the base word representations.
- Non-Parametric Estimation of Multiple Embeddings for Link Prediction on Dynamic Knowledge Graphs67
This paper proposes Parallel Universe TransE (puTransE), an adaptable and robust adaptation of the translational embedding model that non-parametrically estimates the energy score of a triplet from multiple embedding spaces of structurally and semantically aware triplet selection.
- Structural analysis of chat messages for topic detection57
An indicative term‐based categorization approach for chat topic detection is proposed and is superior to the traditional documen...
- Multi-Cast Attention Networks54
This paper proposes Multi-Cast Attention Networks (MCAN), a new attention mechanism and general model architecture for a potpourri of ranking tasks in the conversational modeling and question answering domains and shows that MCAN achieves state-of-the-art performance.
- Multi-Task Neural Network for Non-discrete Attribute Prediction in Knowledge Graphs52
This paper proposes a novel multi-task neural network approach for both encoding and prediction of non-discrete attribute information in a relational setting and shows that this approach outperforms many state-of-the-art methods for the tasks of relational triplet classification and attribute value prediction.
- 51
- An integrated help desk support for customer services over the World Wide Web — a case study50
This paper describes a Web- based integrated system, the WebHotLine system, that possesses Web-based retrieval, online multilingual translation capability for service records, rule-base reasoning for direct intelligent fault diagnosis by customers or service engineers, different modes of video-conferencing for enhanced customer support and network security for secure data communications.
- Hermitian Co-Attention Networks for Text Matching in Asymmetrical Domains49
This paper argues that Co-Attention models in asymmetrical domains require different treatment as opposed to symmetrical domains, and proposes a co-attention mechanism based on the complex-valued inner product (Hermitian products).
- 47
- 46
- 45
- Efficient sequential access pattern mining for web recommendations45
This paper proposes an efficient sequential access pattern mining algorithm, known as CSB-mine (Conditional Sequence Base mining algorithm), which is based directly on the conditional sequence bases of each frequent event which eliminates the need for constructing WAP-trees.
- Cross Temporal Recurrent Networks for Ranking Question Answer Pairs42
This paper explores the idea of learning temporal gates for sequence pairs (question and answer), jointly influencing the learned representations in a pairwise manner and shows that this conceptually simple sharing of temporal gates can lead to competitive performance across multiple benchmarks.
- Exploring ant-based algorithms for gene expression data analysis42
This paper investigates ant-based algorithms for gene expression data clustering and associative classification and finds that Ant-C can generate optimal number of clusters without incorporating any other algorithms such as K-means or agglomerative hierarchical clustering.
- Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences41
This paper proposes Co-Stack Residual Affinity Networks (CSRAN), a new and universal neural architecture for this problem, and introduces a new bidirectional alignment mechanism that learns affinity weights by fusing sequence pairs across stacked hierarchies.
- A math-aware search engine for math question answering system40
This work proposes a math-aware search engine that is capable of handling both textual keywords as well as mathematical expressions and adapts the passive aggressive online learning binary classifier as the ranking model.
- Cursive word reference line detection39
A novel method in detecting the four reference lines of a cursive word at any skew angle by searching for suitable peaks in the Hough transformation space of these points based on points determined by their relative positions between the outer contour and its convex hull.
- 38
- Towards a web-based progressive handwriting recognition environment for mathematical problem solving37
A web-based handwriting mathematics system, called WebMath, for supporting mathematical problem solving, based on client-server architecture, which comprises four major components: a standard web server, handwriting mathematical expression editor, computation engine and web browser with Ajax-based communicator.
- 36
- EvidenceNet: Evidence Fusion Network for Fact Verification34
The experimental results have shown that the proposed EvidenceNet model outperforms the current fact verification methods and achieves the state-of-the-art performance.
- A lattice-based approach for mathematical search using Formal Concept Analysis34
The proposed lattice-based math search approach is benchmarked against a conventional best match retrieval technique and results show it to be almost 10% better in terms of F1 for the top 30 retrieved results.
- 32
- Modularized Interaction Network for Named Entity Recognition32
A novel Modularized Interaction Network (MIN) model is proposed which utilizes both segment-level information and word-level dependencies, and incorporates an interaction mechanism to support information sharing between boundary detection and type prediction to enhance the performance for the NER task.
- 32
- A Formal Concept Analysis Approach for Web Usage Mining32
Formal Concept Analysis, which is based on ordered lattice theory, is applied to mine association rules from web logs and shows that FCA generated 60% fewer rules than Apriori, and the rules are comparable in quality according to three objective measures.
- A Novel Ant-Based Clustering Approach for Document Clustering32
Results show that the ant-based clustering approach outperforms the classical document clustering methods such as K-means and Agglomerate Hierarchical Clustering and achieves better results than those obtained using the Artificial Immune Network algorithm when tested in the same datasets.
- CS-Mine: An Efficient WAP-Tree Mining for Web Access Patterns32
This paper proposes an efficient WAP-tree mining algorithm, known as CS-mine (Conditional Sequence mining algorithm), which is based directly on the initial conditional sequence base of each frequent event and eliminates the need for re-constructing intermediate conditional W AP-trees.
- Mining Frequent Itemsets with Category-Based Constraints32
This paper proposes a specific type of constraints called category-based as well as the associated algorithm for constrained rule mining based on Apriori, which reduces the computational complexity of the mining process by bypassing most of the subsets of the final itemsets.
- Supervised term weighting centroid-based classifiers for text categorization30
An improved centroid-based classifier that uses precise term-class distribution properties instead of presence or absence of terms in classes is proposed, and terms are weighted based on the Kullback–Leibler divergence measure between pairs of class-conditional term probabilities.
- A segment enhanced span-based model for nested named entity recognition29
The proposed Segment Enhanced Span-based model for nested NER has the advantages of enhancing boundary supervision in learning span representations by detecting segment endpoints, reducing the number of negative samples without losing long entities that are ignored by most span-based methods, and improving runtime performance.
- CoupleNet: Paying Attention to Couples with Coupled Attention for Relationship Recommendation27
The CoupleNet is an end-to-end deep learning basedestimator that analyzes the social profiles of two users and subsequently performs a similarity match between the users and is the first data-driven deep learning approach for the novel relationship recommendation problem.
- WEB INFORMATION MONITORING FOR COMPETITIVE INTELLIGENCE27
A web monitoring system, WebMon, to help users monitor specified web pages for latest changes and updates in information and four monitoring functions including date monitoring, keywords monitoring, link monitoring and portion monitoring are supported.
- 25
- Attentive Gated Lexicon Reader with Contrastive Contextual Co-Attention for Sentiment Classification24
This paper introduces a lexicon-driven contextual attention mechanism to imbue lexicon words with long-range contextual information and introduces a contrastive co-attention mechanism that models contrasting polarities between all positive and negative words in a sentence.
- Compositional De-Attention Networks23
This paper proposes a new quasi-attention that is compositional in nature, i.e. built upon the intuition of both similarity and dissimilarity (negative affinity) when computing affinity scores, benefiting from a greater extent of expressiveness.
- 23
- Personalized question recommendation for English grammar learning23
This paper proposes a content‐based approach for personalized grammar question recommendation, which recommends similar grammatical structure and usage questions for further practising and outperforms other classical and state‐of‐the‐art methods in recommending relevant grammar questions.
- 23
- Random Semantic Tensor Ensemble for Scalable Knowledge Graph Link Prediction22
This paper proposes Random Semantic Tensor Ensemble (RSTE), a scalable ensemble-enabled framework based on tensor factorization that samples a knowledge graph tensor in its graph representation and performs link prediction via ensembles of tensorFactorization.
- Effective Named Entity Recognition with Boundary-aware Bidirectional Neural Networks21
The proposed Ba-BNN model is constructed based on the structure of pointer networks for tackling the first problem on boundary tag sparsity and a boundary retraining strategy is proposed to help reduce boundary error propagation caused by the pointer networks in boundary detection and entity classification.
- Enabling Efficient Question Answer Retrieval via Hyperbolic Neural Networks.21
Overall, the proposed approach is a simple neural network that performs question-answer matching and ranking in Hyperbolic space that remains competitive to models with millions of parameters such as Aentive Pooling BiLSTMs or Multi-Perspective Convolutional Neural Networks (MP-CNN).
- Associative feature selection for text mining21
This paper proposes a new feature selection approach for text mining based on association rules that can help reduce the workload of processing huge amounts of data as well as increase the accuracy for the subsequent data mining tasks.
- A framework for evaluating Internet telephony systems21
This paper proposes a framework that utilises a feature and functionality appraisal together with both quantitative and qualitative assessment techniques to allow a systematic evaluation of Internet telephony systems to take place.
- 20
- 20
- Enhancing Mobile Web Access Using Intelligent Recommendations20
This work proposes an implicit server-side approach using intelligent Web recommendations that can significantly enhance the mobile-browsing experience and help typical mobile users efficiently navigate standard Web sites.
- Holographic Factorization Machines for Recommendation18
This paper proposes Holographic Factorization Machines (HFM), a new novel method of enhancing the representation capability of FMs without increasing its parameter size, which replaces the inner product in FMs with holographic reduced representations (HRRs), which are theoretically motivated by associative retrieval and compressed outer products.
- 18
- Automatic Timetabling Using Artificial Immune System18
Empirical study on course timetabling for the School of Computer Engineering, Nanyang Technological University, Singapore as well as the benchmark dataset provided by the Metaheuristic Network shows that the proposed approach gives better results than those obtained using the Genetic Algorithm.
- 16
- Web information monitoring: an analysis of Web page updates16
In this study, a total of 105 Web pages from the Internet were collected and monitored over a one‐month period and different functions and features for a Web monitoring system are identified.
- A hybrid time lagged network for predicting stock prices16
The Hybrid Time Lagged Network (HTLN) is proposed which integrates the supervised Multilayer Perceptron using temporal back-propagation algorithm with the unsupervised Kohonen network for predicting the chaotic stock series to perform more precise prediction.
- 15
- 15
- 14
- 14
- Differentially Private Regression for Discrete-Time Survival Analysis14
This work aims to propose solutions for the regression problem in survival analysis with the protection of differential privacy, and proposes a novel sampling approach based on the Markov Chain Monte Carlo (MCMC) method to practically guarantee differential privacy with better accuracy.
- 14
- 14
- 13
- 13
- A lattice-based approach for chemical structural retrieval12
The proposed lattice-based approach is based on Formal Concept Analysis and retrieves chemical structures that have functional groups and interactions between functional groups similar to the chemical structural query.
- Two-View Online Learning12
The algorithm is an extension of the single-view Passive Aggressive algorithm, where it minimize the changes in the two view weights and disagreements between the two classifiers, and allows the stronger voice (view) to dominate whenever the two views disagree.
- 12
- A web usage lattice based mining approach for intelligent web personalization12
The proposed WUL‐based mining approach aims to mine a reduced set of effective association pattern rules for enhancing the online performance of web recommendations and is incorporated into a personalized web recommender system known as AWARS.
- PubSearch: a Web citation‐based retrieval system12
PubSearch proposes a Web citation‐based retrieval system, known as PubSearch, for the retrieval of Web publications, which indexes Web publications based on citation indices and stores them into a Web Citation Database.
- Security considerations in the delivery of Web‐based applications: a case study12
Login passwords are used to achieve user authentication, provide a safeguard against replay attacks, and prevent non‐repudiatory usage of system by users and a security solution is proposed that employs a combination of Web server security measures and cryptographic techniques.
- Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension11
A new compositional encoder for reading comprehension (RC) that explicitly models across multiple granularities using a new dilated composition mechanism, enabling compositional learning that is aware of both long and short term information.
- Ontology-Based Fuzzy Retrieval for Digital Library10
This paper proposes an architecture that enables multiple digital libraries to collaborate in the Semantic Web environment and discusses using fuzzy ontology to represent uncertain information in digital libraries and fuzzy queries for retrieving information from fuzzy Ontology.
- 10
- 9
- Dialogue State Distillation Network with Inter-slot Contrastive Learning for Dialogue State Tracking9
- Divide-and-conquer memetic algorithm for online multi-objective test paper generation9
An efficient multi-objective optimization approach based on the divide-and-conquer memetic algorithm (DAC-MA) for Online-TPG is proposed, which has outperformed other TPG techniques in terms of runtime efficiency and paper quality.
- Adaptive Two-View Online Learning for Math Topic Classification9
This paper proposes a novel adaptive two-view online math document classifier based on the Passive Aggressive (PA) algorithm, which is evaluated on real world math questions and answers from the Math Overflow question answering system.
- 9
- Artificial Immune System for Associative Classification9
The proposed AIS-AC approach is efficient in dealing with the complexity problem on the large search space of rules, and is able to find an effective set of associative rules for classification.
- Wireless messaging services for mobile users9
A number of techniques such as compression, on-demand retrieval, multi-part retrieval, content summarization and attachment conversion to support wireless messaging are incorporated into the Wireless Messaging Gateway System (WMGS) which supports e-mail, fax, voice mail, paging and short messaging services for the integrated Internet and wireless environment.
- 8
- 8
- 8
- 7
- Mining Multiple Clustering Data for Knowledge Discovery7
An effective approach known as Multi-Clustering to mine the data generated from different clustering methods for discovering relationships between clusters of data and discusses an application example that uses the proposed technique toMine the author clusters and document clusters for identifying the relationships on authors working on research areas.
- 6
- A syntactic evidence network model for fact verification6
The proposed SENet model has outperformed the baseline models and achieved the state-of-the-art performance for fact verification and the sentence attention mechanism is applied to obtain a richer semantic representation.
- Syntactic based approach for grammar question retrieval6
This paper proposes a syntactic based approach for English grammar question retrieval which can retrieve related grammar questions with similar grammatical focus effectively and outperforms the state-of-the-art methods based on statistical analysis and syntactic analysis.
- 6
- 6
- Ontology-Based Natural Query Retrieval Using Conceptual Graphs6
A novel ontology-based approach for natural query retrieval of scholarly information using conceptual graphs is proposed and some promising initial results are presented.
- An Efficient Approach for Mining Periodic Sequential Access Patterns6
This paper proposes an efficient approach, known as TCS-mine (Temporal Conditional Sequence mining algorithm), for mining periodic sequential access patterns based on calendar-based periodic time constraints, which can be used for temporal-based personalized web recommendations.
- Unified personal mobile communication services for a wireless campus6
A personal communications system that integrates various services into a unified platform, providing a one‐stop source for both information access and communication within a wireless campus environment is described.
- A Hybrid Case-Based Reasoning and Neural Network Approach to Online Intelligent Fault Diagnosis.6
A hybrid case-based reasoning (CBR) and artificial neural network (ANN) approach for intelligent fault diagnosis is described that integrates ANN with the CBR cycle to extract knowledge from service records of the customer service database and subsequently recall the appropriate service records using this knowledge during the retrieval phase.
- Approaches for resolving dynamic IP addressing6
Of these methods, the dynamic Domain Name System and directory service look‐up appear to be the best for resolving dynamic IP addressing.
- Utilizing Temporal Information for Taxonomy Construction5
A time-aware method to automatically construct and effectively maintain a taxonomy from a given series of documents preclustered for a domain of interest and can incrementally update the taxonomy by adding fresh relations from new data and removing outdated relations using an information decay function.
- Web-Based Mathematics Testing with Automatic Assessment5
The proposed framework consists of an efficient constraint-based Divide-and-Conquer approach for automatic test paper generation, and an effective Probabilistic Equivalence Verification algorithm for automatic mathematical answer verification.
- 5
- Web Mining for Identifying Research Trends5
This paper will discuss the proposed web mining approach, the performance of the proposed approach, and the knowledge that is mined from the inter-relationships is used for the detection of trends and emergent trends for a specified research area.
- 4
- 4
- 4
- Gated Character-aware Convolutional Neural Network for Effective Automated Essay Scoring4
The experimental results show that the proposed GCCNN model outperforms the baseline deep learning models and the qualitative analysis demonstrates the importance of character-level information for tackling the out-of-vocabulary problem in grading essays.
- Content-Based Collaborative Filtering for Question Difficulty Calibration4
An effective Content-based Collaborative Filtering (CCF) approach for automatic calibration of question difficulty degree and its performance evaluation in comparison with other techniques is presented.
- 4
- A multimodal restaurant finder for semantic web4
A semantic multimodal system, called Semantic Restaurant Finder, is proposed for the Semantic Web in which the restaurant information in different city/country/language are constructed as ontologies to allow the information to be sharable.
- Monitoring Web Information using PBD Technique4
A web monitoring system, WebMon, is proposed to help users to track a specific portion of a web page for updates and the technique for implementing portion monitoring is based on Programming by Demonstration (PBD).
- Effective type label-based synergistic representation learning for biomedical event trigger detection3
The proposed BioLSL model demonstrates good performance for biomedical event trigger detection without using any external resources, which suggests that label representation learning and context-aware enhancement are promising directions for improving the task.
- GranCATs: Cross-Lingual Enhancement through Granularity-Specific Contrastive Adapters3
The effectiveness of the proposed GranCATs in enhancing cross-lingual alignments across various text granularities and effectively transferring this knowledge to downstream tasks is validated.
- 3
- HyperQA: Hyperbolic Embeddings for Fast and Efficient Ranking of Question Answer Pairs3
HyperQA is presented, a parameter ecient neural network model that outperforms several parameter heavy models such as Aentive Pooling BiLSTMs and Multi Perspective CNN on multiple standard benchmark datasets such as TrecQA, WikiQA and YahooQA.
- Probabilistic equivalence verification approach for automatic mathematical solution assessment3
The proposed PEV approach is a randomized method based on the probabilistic numerical equivalence testing of two mathematical expressions that can avoid false negative errors completely while guaranteeing a small probability of false positive errors to occur.
- Functional Feature Extraction and Chemical Retrieval3
This paper proposes a new approach for chemical feature extraction and retrieval that achieves promising accuracy and outperforms a state-of-the-art method for chemical retrieval.
- A Divide-and-Conquer Tabu Search Approach for Online Test Paper Generation3
The proposed DAC-TS approach, based on the principle of constraint-based divide-and-conquer and tabu search for constraint decomposition and multi-objective optimization for Online-TPG, has outperformed other techniques in terms of runtime and paper quality.
- Mining Class Association Rules with Artificial Immune System3
A new approach known as AIS-AC, which is based on Artificial Immune System (AIS), is proposed, for mining class association rules for associative classification, which will only find a subset of association rules suitable for effective association classification in an evolutionary manner.
- Mining Association Rules Using Relative Confidence3
The effectiveness of the relative confidence measure is evaluated in comparison with the confidence measure in mining interesting relationships between terms from textual documents and in associative classification.
- CLOG: A class-based logic language for object-oriented databases3
A class-based logic language for object-oriented databases which is called CLOG is described, based on many sorted horn clauses with concept of classes, objects, object identity, multiple class membership of objects and non-monotonic inheritance.
- Concept-enhanced heterogeneous graph network for fact verification2
The experimental results indicate that the Concept-HGN model proposed in this paper outperforms the baseline models and achieves state-of-the-art performance on the task of fact verification.
- Privacy-Preserving Mechanisms for Parametric Survival Analysis with Weibull Distribution2
It is proved that the proposed mechanisms for parametric survival analysis with Weibull distribution achieve differential privacy, a robust and rigorous definition of privacy-preservation.
- 2
- 2
- 2
- Associative Classification with Prediction Confidence2
A measure called prediction confidence is proposed to measure the prediction accuracy of association rules to improve the performance of associative classifiers and a probabilistic-based approach for estimating prediction confidence of associationrules is given.
- Monitoring scientific publications over the WWW2
A publication monitoring system, known as PubWatcher, is proposed to automatically track Web publications from user‐specified Web sites or pages and a publication extraction technique has been developed to extract publication information listed in the index pages of the monitored Web sites and pages.
- Automatic thesaurus for enhanced Chinese text retrieval2
A process for generating an automatic Chinese thesaurus that can be used to provide related terms to a user’s queries to enhance retrieval effectiveness and was confirmed to improve the retrieval effectiveness of a Chinese IR system.
- 1
- 1
- 1
- Semantic Pivoting Model for Effective Event Detection1
A Semantic Pivoting Model for Effective Event Detection (SPEED) is proposed, which explicitly incorporates prior information during training and captures semantically meaningful correlations between input and events.
- A Syntactic Parse-Key Tree-Based Approach for English Grammar Question Retrieval1
A syntactic parse-key tree based approach for English grammar question retrieval which can find relevant grammar questions with similar grammatical focus effectively and outperforms other classical text and sentence retrieval methods in accuracy.
- 1
- A Fax Adapter for Internet Fax-To-Fax Communication1
An Internet fax adapter (IFA) is designed to provide a seamless interface for traditional fax users to do Internet faxing without changing the mode of faxing operations they are familiar with.
- RTFaxing : Internet real-time faxing system1
An Adaptive Control and Recovery (ACR) mechanism for supporting real-time fax communications over the Internet is proposed and implemented into RTFaxing, an Internet Real-Time Faxing System that was developed at the School of Applied Science, Nanyang Technological University, Singapore.
- –
- –
- Privacy Protection for Flexible Parametric Survival Models–
Two solutions to the privacy-preserving problem of regression models on medical data are proposed, focusing on flexible parametric models which are powerful alternatives to the well-known Cox regression model.
- Collective biobjective optimization algorithm for parallel test paper generation–
CBO is a multi-step greedy-based approximation algorithm, which exploits the submodular property for biobjective optimization of k-TPG and has drastically outperformed the current techniques in terms of paper quality and runtime efficiency.
- Chemical Symbol Feature Set for Handwritten Chemical Symbol Recognition–
This paper proposes a novel CF44 chemical feature set based on the trajectory-based recognition approach and the performance of the proposed chemical features is evaluated with promising results using a chemical formula recognition system.
- –
- A multimedia call on the Internet–
A system architecture to support multimedia call centre that isbrowser-based, able to support video, audio and collaborative tools such as whiteboard, chat, file sharing, co-filling of forms and cobrowsing of web sites is proposed.
- –
- –
- A Multimedia Call Centre on the Internet–
A system architecture to support multimedia call centre that is able to support video, audio and collaborative tools such as whiteboard, chat, file sharing, co-filling of forms and cobrowsing of web sites is proposed.
- –
- A web-based Internet Java Phone for real-time voice communication–
A web-based Internet Java Phone (or IJPhone) which can be downloaded from the Internet and run from standard Java-compliant web browser, is proposed in this paper.
- Delivery of video mail on the World Wide Web–
This paper examines a number of possible system architectures that can be employed for the development of video mail and addresses implementation issues pertaining to the use of CGI programs, mail server development, and video and audio management.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-10. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.