Databases and Information Systems Commons^™

Cornac: A Comparative Framework For Multimodal Recommender Systems, Aghiles Salah, Quoc Tuan Truong, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Cornac is an open-source Python framework for multimodal recommender systems. In addition to core utilities for accessing, building, evaluating, and comparing recommender models, Cornac is distinctive in putting emphasis on recommendation models that leverage auxiliary information in the form of a social network, item textual descriptions, product images, etc. Such multimodal auxiliary data supplement user-item interactions (e.g., ratings, clicks), which tend to be sparse in practice. To facilitate broad adoption and community contribution, Cornac is publicly available at https://github.com/PreferredAI/cornac, and it can be installed via Anaconda or the Python Package Index (pip). Not only is it well-covered by unit tests …

Are These Comments Triggering? Predicting Triggers Of Toxicity In Online Discussions, Hind Almerekhi, Haewoon Kwak, Joni Salminen, Bernard J. Jansen

Research Collection School Of Computing and Information Systems

Understanding the causes or triggers of toxicity adds a new dimension to the prevention of toxic behavior in online discussions. In this research, we define toxicity triggers in online discussions as a non-toxic comment that lead to toxic replies. Then, we build a neural network-based prediction model for toxicity trigger. The prediction model incorporates text-based features and derived features from previous studies that pertain to shifts in sentiment, topic flow, and discussion context. Our findings show that triggers of toxicity contain identifiable features and that incorporating shift features with the discussion context can be detected with a ROC-AUC score of …

Improving Neural Relation Extraction With Implicit Mutual Relations, Jun Kuang, Yixin Cao, Jianbing Zheng, Xiangnan He, Ming Gao, Aoying Zhou

Research Collection School Of Computing and Information Systems

Relation extraction (RE) aims at extracting the relation between two entities from the text corpora. It is a crucial task for Knowledge Graph (KG) construction. Most existing methods predict the relation between an entity pair by learning the relation from the training sentences, which contain the targeted entity pair. In contrast to existing distant supervision approaches that suffer from insufficient training corpora to extract relations, our proposal of mining implicit mutual relation from the massive unlabeled corpora transfers the semantic information of entity pairs into the RE model, which is more expressive and semantically plausible. After constructing an entity proximity …

Review-Guided Helpful Answer Identification In E-Commerce, Wenxuan Zhang, Wai Lam, Yang Deng, Jing Ma

Research Collection School Of Computing and Information Systems

Product-specific community question answering platforms can greatly help address the concerns of potential customers. However, the user-provided answers on such platforms often vary a lot in their qualities. Helpfulness votes from the community can indicate the overall quality of the answer, but they are often missing. Accurately predicting the helpfulness of an answer to a given question and thus identifying helpful answers is becoming a demanding need. Since the helpfulness of an answer depends on multiple perspectives instead of only topical relevance investigated in typical QA tasks, common answer selection algorithms are insufficient for tackling this task. In this paper, …

Reinforced Negative Sampling Over Knowledge Graph For Recommendation, Xiang Wang, Yaokun Xu, Xiangnan He, Yixin Cao, Meng Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Properly handling missing data is a fundamental challenge in recommendation. Most present works perform negative sampling from unobserved data to supply the training of recommender models with negative signals. Nevertheless, existing negative sampling strategies, either static or adaptive ones, are insufficient to yield high-quality negative samples — both informative to model training and reflective of user real needs. In this work, we hypothesize that item knowledge graph (KG), which provides rich relations among items and KG entities, could be useful to infer informative and factual negative samples. Towards this end, we develop a new negative sampling model, Knowledge Graph Policy …

Artificial Intelligence (Ai) Ethics: Ethics Of Ai And Ethical Ai, Keng Siau, Weiyu Wang

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI)-based technology has achieved many great things, such as facial recognition, medical diagnosis, and self-driving cars. AI promises enormous benefits for economic growth, social development, as well as human well-being and safety improvement. However, the low-level of explainability, data biases, data security, data privacy, and ethical problems of AI-based technology pose significant risks for users, developers, humanity, and societies. As AI advances, one critical issue is how to address the ethical and moral challenges associated with AI. Even though the concept of “machine ethics” was proposed around 2006, AI ethics is still in the infancy stage. AI ethics …

Recipegpt: Generative Pre-Training Based Cooking Recipe Generation And Evaluation System, Helena Huey Chong Lee, Ke Shu, Palakorn Achananuparp, Philips Kokoh Prasetyo, Yue Liu, Ee-Peng Lim, Lav R. Varshney

Research Collection School Of Computing and Information Systems

Interests in the automatic generation of cooking recipes have been growing steadily over the past few years thanks to a large amount of online cooking recipes. We present RecipeGPT, a novel online recipe generation and evaluation system. The system provides two modes of text generations: (1) instruction generation from given recipe title and ingredients; and (2) ingredient generation from recipe title and cooking instructions. Its back-end text generation module comprises a generative pre-trained language model GPT-2 fine-tuned on a large cooking recipe dataset. Moreover, the recipe evaluation module allows the users to conveniently inspect the quality of the generated recipe …

A Cue Adaptive Decoder For Controllable Neural Response Generation, Weichao Wang, Shi Feng, Wei Gao, Daling Wang, Yifei Zhang

Research Collection School Of Computing and Information Systems

In open-domain dialogue systems, dialogue cues such as emotion, persona, and emoji can be incorporated into conversation models for strengthening the semantic relevance of generated responses. Existing neural response generation models either incorporate dialogue cue into decoder’s initial state or embed the cue indiscriminately into the state of every generated word, which may cause the gradients of the embedded cue to vanish or disturb the semantic relevance of generated words during back propagation. In this paper, we propose a Cue Adaptive Decoder (CueAD) that aims to dynamically determine the involvement of a cue at each generation step in the decoding. …

Voicecoach: Interactive Evidence-Based Training For Voice Modulation Skills In Public Speaking, Xingbo Wang, Haipeng Zeng, Yong Wang, Aoyu Wu, Zhida Sun, Xiaojuan Ma, Qu Huamin

Research Collection School Of Computing and Information Systems

The modulation of voice properties, such as pitch, volume, and speed, is crucial for delivering a successful public speech. However, it is challenging to master different voice modulation skills. Though many guidelines are available, they are often not practical enough to be applied in different public speaking situations, especially for novice speakers. We present VoiceCoach, an interactive evidence-based approach to facilitate the effective training of voice modulation skills. Specifically, we have analyzed the voice modulation skills from 2623 high-quality speeches (i.e., TED Talks) and use them as the benchmark dataset. Given a voice input, VoiceCoach automatically recommends good voice modulation …

Poster Abstract: Data Communication Using Switchable Privacy Glass, Changshuo Hu, Dong Ma, Mahbub Hassan, Wen Hu

Research Collection School Of Computing and Information Systems

Switchable privacy glass can electronically change its state between opaque and transparent. In this work, we propose to exploit the electronic configurability of switchable glass to modulate natural light, which can be demodulated by a nearby receiver with light sensing capability to realise data communication over natural light. A key advantage is that no energy is used to generate light, as it simply modulates the existing light in the nature. We demonstrate that the proposed data communication using switchable glass modulation can achieve 33.33 bits per second communication with a bit rate below 1% under a wide range of ambient …

Predictive Task Assignment In Spatial Crowdsourcing: A Data-Driven Approach, Yan Zhao, Kai Zheng, Yue Cui, Han Su, Feida Zhu, Xiaofang Zhou

Research Collection School Of Computing and Information Systems

With the rapid development of mobile networks and the widespread usage of mobile devices, spatial crowdsourcing, which refers to assigning location-based tasks to moving workers, has drawn increasing attention. One of the major issues in spatial crowdsourcing is task assignment, which allocates tasks to appropriate workers. However, existing works generally assume the static offline scenarios, where the spatio-temporal information of all the workers and tasks is determined and known a priori. Ignorance of the dynamic spatio-temporal distributions of workers and tasks can often lead to poor assignment results. In this work we study a novel spatial crowdsourcing problem, namely Predictive …

Light Structure From Pin Motion: Geometric Point Light Source Calibration, Hiroaki Santo, Michael Waechter, Wen-Yan Lin, Yusuke Sugano, Yasuyuki Matsushita

Research Collection School Of Computing and Information Systems

We present a method for geometric point light source calibration. Unlike prior works that use Lambertian spheres, mirror spheres, or mirror planes, we use a calibration target consisting of a plane and small shadow casters at unknown positions above the plane. We show that shadow observations from a moving calibration target under a fixed light follow the principles of pinhole camera geometry and epipolar geometry, allowing joint recovery of the light position and 3D shadow caster positions, equivalent to how conventional structure from motion jointly recovers camera parameters and 3D feature positions from observed 2D features. Moreover, we devised a …

Using Knowledge Bases For Question Answering, Yunshi Lan

Dissertations and Theses Collection (Open Access)

A knowledge base (KB) is a well-structured database, which contains many of entities and their relations. With the fast development of large-scale knowledge bases such as Freebase, DBpedia and YAGO, knowledge bases have become an important resource, which can serve many applications, such as dialogue system, textual entailment, question answering and so on. These applications play significant roles in real-world industry.

In this dissertation, we try to explore the entailment information and more general entity-relation information from the KBs. Recognizing textual entailment (RTE) is a task to infer the entailment relations between sentences. We need to decide whether a hypothesis …

Towards K-Vertex Connected Component Discovery From Large Networks, Li Yuan, Guoren Wang, Yuhai Zhao, Feida Zhu

Research Collection School Of Computing and Information Systems

In many real life network-based applications such as social relation analysis, Web analysis, collaborative network, road network and bioinformatics, the discovery of components with high connectivity is an important problem. In particular, k-edge connected component (k-ECC) has recently been extensively studied to discover disjoint components. Yet many real scenarios present more needs and challenges for overlapping components. In this paper, we propose a k-vertex connected component (k-VCC) model, which is much more cohesive, and thus supports overlapping between components very well. To discover k-VCCs, we propose three frameworks including top-down, bottom-up and hybrid …

Using Reinforcement Learning To Minimize The Probability Of Delay Occurrence In Transportation, Zhiguang Cao, Hongliang Guo, Wen Song, Kaizhou Gao, Zhengghua Chen, Le Zhang, Xuexi Zhang

Research Collection School Of Computing and Information Systems

Reducing traffic delay is of crucial importance for the development of sustainable transportation systems, which is a challenging task in the studies of stochastic shortest path (SSP) problem. Existing methods based on the probability tail model to solve the SSP problem, seek for the path that minimizes the probability of delay occurrence, which is equal to maximizing the probability of reaching the destination before a deadline (i.e., arriving on time). However, they suffer from low accuracy or high computational cost. Therefore, we design a novel and practical Q-learning approach where the converged Q-values have the practical meaning as the actual …

Detecting Fake News In Social Media: An Asia-Pacific Perspective, Meeyoung Cha, Wei Gao, Cheng-Te Li

Research Collection School Of Computing and Information Systems

In March 2011, the catastrophic accident known as "The Fukushima Daiichi nuclear disaster" took place, initiated by the Tohoku earthquake and tsunami in Japan. The only nuclear accident to receive a Level-7 classification on the International Nuclear Event Scale since the Chernobyl nuclear power plant disaster in 1986, the Fukushima event triggered global concerns and rumors regarding radiation leaks. Among the false rumors was an image, which had been described as a map of radioactive discharge emanating into the Pacific Ocean, as illustrated in the accompanying figure. In fact, this figure, depicting the wave height of the tsunami that followed, …

Feature Agglomeration Networks For Single Stage Face Detection, Jialiang Zhang, Xiongwei Wu, Steven C. H. Hoi, Jianke Zhu

Research Collection School Of Computing and Information Systems

Recent years have witnessed promising results of exploring deep convolutional neural network for face detection. Despite making remarkable progress, face detection in the wild remains challenging especially when detecting faces at vastly different scales and characteristics. In this paper, we propose a novel simple yet effective framework of “Feature Agglomeration Networks” (FANet) to build a new single-stage face detector, which not only achieves state-of-the-art performance but also runs efficiently. As inspired by Feature Pyramid Networks (FPN) (Lin et al., 2017), the key idea of our framework is to exploit inherent multi-scale features of a single convolutional neural network by aggregating …

The Spatial Optimization And Evaluation Of The Economic, Ecological, And Social Value Of Urban Green Space In Shenzhen, Yuhan Yu, Wenting Zhang, Peihong Fu, Wei Huang, Keke Li, Kai Cao

Research Collection School Of Computing and Information Systems

Urban green space (UGS) is important in urban systems, as it benefits economic development, ecological conservation, and living conditions. Many studies have evaluated the economic, ecological, and social value of UGS worldwide, and spatial optimization for UGS has been carried out to maximize its value. However, few studies have simultaneously examined these three values of UGS in one optimization system. To fill this gap, this study evaluated the economic value of UGS in terms of promoting housing prices, its ecological value through the relief of high land surface temperature (LST), and its social value through the provision of recreation spaces …

The Search For Optimal Oxygen Saturation Targets In Critically Ill: Patients Observational Data From Large Icu Databases, Willem Van Den Boom, Michael Hoy, Jagadish Sankaran, Mengru Liu, Haroun Chahed, Mengling Feng, Kay Choong See

Research Collection School Of Computing and Information Systems

Background: Although low oxygen saturations are generally regarded as deleterious, recent studies in ICU patients have shown that a liberal oxygen strategy increases mortality. However, the optimal oxygen saturation target remains unclear. The goal of this study was to determine the optimal range by using real-world data. Methods: Replicate retrospective analyses were conducted of two electronic medical record databases: the eICU Collaborative Research Database (eICU-CRD) and the Medical Information Mart for Intensive Care III database (MIMIC). Only patients with at least 48 h of oxygen therapy were included. Nonlinear regression was used to analyze the association between median pulse oximetry-derived …

Privacy-Preserving Data Processing With Flexible Access Control, Wenxiu Ding, Zheng Yan, Robert H. Deng

Research Collection School Of Computing and Information Systems

Cloud computing provides an efficient and convenient platform for cloud users to store, process and control their data. Cloud overcomes the bottlenecks of resource-constrained user devices and greatly releases their storage and computing burdens. However, due to the lack of full trust in cloud service providers, the cloud users generally prefer to outsource their sensitive data in an encrypted form, which, however, seriously complicates data processing, analysis, as well as access control. Homomorphic encryption (HE) as a single key system cannot flexibly control data sharing and access after encrypted data processing. How to realize various computations over encrypted data in …

Mcdpc: Multi‐Center Density Peak Clustering, Yizhang Wang, Di Wang, Xiaofeng Zhang, Wei Pang, Chunyan Miao, Ah-Hwee Tan, You Zhou

Research Collection School Of Computing and Information Systems

Density peak clustering (DPC) is a recently developed density-based clustering algorithm that achieves competitive performance in a non-iterative manner. DPC is capable of effectively handling clusters with single density peak (single center), i.e., based on DPC’s hypothesis, one and only one data point is chosen as the center of any cluster. However, DPC may fail to identify clusters with multiple density peaks (multi-centers) and may not be able to identify natural clusters whose centers have relatively lower local density. To address these limitations, we propose a novel clustering algorithm based on a hierarchical approach, named multi-center density peak clustering (McDPC). …

Interpretable Rumor Detection In Microblogs By Attending To User Interactions, Ling Min Serena Khoo, Hai Leong Chieu, Zhong Qian, Jing Jiang

Research Collection School Of Computing and Information Systems

We address rumor detection by learning to differentiate between the community’s response to real and fake claims in microblogs. Existing state-of-the-art models are based on tree models that model conversational trees. However, in social media, a user posting a reply might be replying to the entire thread rather than to a specific user. We propose a post-level attention model (PLAN) to model long distance interactions between tweets with the multi-head attention mechanism in a transformer network. We investigated variants of this model: (1) a structure aware self-attention model (StA-PLAN) that incorporates tree structure information in the transformer network, and (2) …

Joint Learning Of Answer Selection And Answer Summary Generation In Community Question Answering, Yang Deng, Wai Lam, Yuexiang Xie, Daoyuan Chen, Yaliang Li, Min Yang, Ying Shen

Research Collection School Of Computing and Information Systems

Community question answering (CQA) gains increasing popularity in both academy and industry recently. However, the redundancy and lengthiness issues of crowdsourced answers limit the performance of answer selection and lead to reading difficulties and misunderstandings for community users. To solve these problems, we tackle the tasks of answer selection and answer summary generation in CQA with a novel joint learning model. Specifically, we design a question-driven pointer-generator network, which exploits the correlation information between question-Answer pairs to aid in attending the essential information when generating answer summaries. Meanwhile, we leverage the answer summaries to alleviate noise in original lengthy answers …

Topic Modeling On Document Networks With Adjacent-Encoder, Ce Zhang, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Oftentimes documents are linked to one another in a network structure,e.g., academic papers cite other papers, Web pages link to other pages. In this paper we propose a holistic topic model to learn meaningful and unified low-dimensional representations for networked documents that seek to preserve both textual content and network structure. On the basis of reconstructing not only the input document but also its adjacent neighbors, we develop two neural encoder architectures. Adjacent-Encoder, or AdjEnc, induces competition among documents for topic propagation, and reconstruction among neighbors for semantic capture. Adjacent-Encoder-X, or AdjEnc-X, extends this to also encode the network structure …

Deepdualmapper: A Gated Fusion Network For Automatic Map Extraction Using Aerial Images And Trajectories, Hao Wu, Hanyuan Zhang, Xinyu Zhang, Weiwei Sun, Baihua Zheng, Yuning Jiang

Research Collection School Of Computing and Information Systems

Automatic map extraction is of great importance to urban computing and location-based services. Aerial image and GPS trajectory data refer to two different data sources that could be leveraged to generate the map, although they carry different types of information. Most previous works on data fusion between aerial images and data from auxiliary sensors do not fully utilize the information of both modalities and hence suffer from the issue of information loss. We propose a deep convolutional neural network called DeepDualMapper which fuses the aerial image and trajectory data in a more seamless manner to extract the digital map. We …

Multi-Level Head-Wise Match And Aggregation In Transformer For Textual Sequence Matching, Shuohang Wang, Yunshi Lan, Yi Tay, Jing Jiang, Jingjing Liu

Research Collection School Of Computing and Information Systems

Transformer has been successfully applied to many natural language processing tasks. However, for textual sequence matching, simple matching between the representation of a pair of sequences might bring in unnecessary noise. In this paper, we propose a new approach to sequence pair matching with Transformer, by learning head-wise matching representations on multiple levels. Experiments show that our proposed approach can achieve new state-of-the-art performance on multiple tasks that rely only on pre-computed sequence-vectorrepresentation, such as SNLI, MNLI-match, MNLI-mismatch, QQP, and SQuAD-binary

Image Enhanced Event Detection In News Articles, Meihan Tong, Shuai Wang, Yixin Cao, Bin Xu, Juaizi Li, Lei Hou, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Event detection is a crucial and challenging sub-task of event extraction, which suffers from a severe ambiguity issue of trigger words. Existing works mainly focus on using textual context information, while there naturally exist many images accompanied by news articles that are yet to be explored. We believe that images not only reflect the core events of the text, but are also helpful for the disambiguation of trigger words. In this paper, we first contribute an image dataset supplement to ED benchmarks (i.e., ACE2005) for training and evaluation. We then propose a novel Dual Recurrent Multimodal Model, DRMM, to conduct …

Stochastically Robust Personalized Ranking For Lsh Recommendation Retrieval, Dung D. Le, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Locality Sensitive Hashing (LSH) has become one of the most commonly used approximate nearest neighbor search techniques to avoid the prohibitive cost of scanning through all data points. For recommender systems, LSH achieves efficient recommendation retrieval by encoding user and item vectors into binary hash codes, reducing the cost of exhaustively examining all the item vectors to identify the topk items. However, conventional matrix factorization models may suffer from performance degeneration caused by randomly-drawn LSH hash functions, directly affecting the ultimate quality of the recommendations. In this paper, we propose a framework named SRPR, which factors in the stochasticity of …

Migrating From Monoliths To Cloud-Based Microservices: A Banking Industry Example, Alan Megargel, Venky Shankararaman, David K. Walker

Research Collection School Of Computing and Information Systems

As more organizations are placing cloud computing at the heart of their digital transformation strategy, it is important that they adopt appropriate architectures and development methodologies to leverage the full benefits of the cloud. A mere “lift and move” approach, where traditional monolith applications are moved to the cloud will not support the demands of digital services. While, monolithic applications may be easier to develop and control, they are inflexible to change and lack the scalability needed for cloud environments. Microservices architecture, which adopts some of the concepts and principles from service-oriented architecture, provides a number of benefits when developing …

The Future Of Work Now: Medical Coding With Ai, Thomas H. Davenport, Steven M. Miller

Research Collection School Of Computing and Information Systems

The coding of medical diagnosis and treatment has always been a challenging issue. Translating a patient’s complex symptoms, and a clinician’s efforts to address them, into a clear and unambiguous classification code was difficult even in simpler times. Now, however, hospitals and health insurance companies want very detailed information on what was wrong with a patient and the steps taken to treat them— for clinical record-keeping, for hospital operations review and planning, and perhaps most importantly, for financial reimbursement purposes.