Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (8549)
- Computer Sciences (8532)
- Databases and Information Systems (3451)
- Software Engineering (2164)
- Artificial Intelligence and Robotics (1697)
-
- Information Security (1067)
- Numerical Analysis and Scientific Computing (1024)
- Engineering (956)
- Graphics and Human Computer Interfaces (933)
- Social and Behavioral Sciences (734)
- Business (686)
- Computer Engineering (512)
- Theory and Algorithms (493)
- Operations Research, Systems Engineering and Industrial Engineering (417)
- Programming Languages and Compilers (379)
- OS and Networks (323)
- Communication (310)
- Social Media (248)
- Public Affairs, Public Policy and Public Administration (227)
- Transportation (204)
- Medicine and Health Sciences (186)
- Education (180)
- Management Information Systems (178)
- Data Storage Systems (176)
- E-Commerce (151)
- International and Area Studies (125)
- Asian Studies (124)
- Digital Communications and Networking (123)
- Technology and Innovation (114)
- Health Information Technology (113)
- Keyword
-
- Machine learning (125)
- Deep learning (124)
- Social media (80)
- Artificial intelligence (72)
- Reinforcement learning (69)
-
- Data mining (65)
- Privacy (65)
- Cloud computing (58)
- Deep Learning (56)
- Empirical study (55)
- Optimization (55)
- Security (54)
- Singapore (52)
- Visualization (52)
- Task analysis (50)
- Twitter (50)
- Neural networks (49)
- Online learning (49)
- Software engineering (49)
- Training (49)
- Anomaly detection (47)
- Feature extraction (46)
- Collaboration (45)
- Large Language Models (45)
- Blockchain (44)
- Semantics (43)
- Access control (41)
- Algorithms (40)
- Android (39)
- Natural language processing (39)
- Publication Year
- File Type
Articles 2731 - 2760 of 8722
Full-Text Articles in Entire DC Network
Quantum Computing For Supply Chain Finance, Paul R. Griffin, Ritesh Sampat
Quantum Computing For Supply Chain Finance, Paul R. Griffin, Ritesh Sampat
Research Collection School Of Computing and Information Systems
Applying quantum computing to real world applications to assess the potential efficacy is a daunting task for non-quantum specialists. This paper shows an implementation of two quantum optimization algorithms applied to portfolios of trade finance portfolios and compares the selections to those chosen by experienced underwriters and a classical optimizer. The method used is to map the financial risk and returns for a trade finance portfolio to an optimization function of a quantum algorithm developed in a Qiskit tutorial. The results show that whilst there is no advantage seen by using the quantum algorithms, the performance of the quantum algorithms …
Unified And Incremental Simrank: Index-Free Approximation With Scheduled Principle, Fanwei Zhu, Yuan Fang, Kai Zhang, Kevin C.-C. Chang, Hongtai Cao, Zhen Jiang, Minghui Wu
Unified And Incremental Simrank: Index-Free Approximation With Scheduled Principle, Fanwei Zhu, Yuan Fang, Kai Zhang, Kevin C.-C. Chang, Hongtai Cao, Zhen Jiang, Minghui Wu
Research Collection School Of Computing and Information Systems
SimRank is a popular link-based similarity measure on graphs. It enables a variety of applications with different modes of querying (e.g., single-pair, single-source and all-pair modes). In this paper, we propose UISim, a unified and incremental framework for all SimRank modes based on a scheduled approximation principle. UISim processes queries with incremental and prioritized exploration of the entire computation space, and thus allows flexible tradeoff of time and accuracy. On the other hand, it creates and shares common “building blocks” for online computation without relying on indexes, and thus is efficient to handle both static and dynamic graphs. Our experiments …
Few-Shot Breast Cancer Metastases Classification Via Unsupervised Cell Ranking, Jiaojiao Chen, Jianbo Jiao, Shengfeng He, Guoqiang Han, Jing Qin
Few-Shot Breast Cancer Metastases Classification Via Unsupervised Cell Ranking, Jiaojiao Chen, Jianbo Jiao, Shengfeng He, Guoqiang Han, Jing Qin
Research Collection School Of Computing and Information Systems
Tumor metastases detection is of great importance for the treatment of breast cancer patients. Various CNN (convolutional neural network) based methods get excellent performance in object detection/ segmentation. However, the detection of metastases in hematoxylin and eosin (H&E) stained whole-slide images (WSI) is still challenging mainly due to two aspects. (1) The resolution of the image is too large. (2) lacking labeled training data. Whole-slide images generally stored in a multi-resolution structure with multiple downsampled tiles. It is difficult to feed the whole image into memory without compression. Moreover, labeling images for the pathologists are time-consuming and expensive. In this …
Which Variables Should I Log?, Zhongxin Liu, Xin Xia, David Lo, Zhenchang Xing, Ahmed E. Hassan, Shanping Li
Which Variables Should I Log?, Zhongxin Liu, Xin Xia, David Lo, Zhenchang Xing, Ahmed E. Hassan, Shanping Li
Research Collection School Of Computing and Information Systems
Developers usually depend on inserting logging statements into the source code to collect system runtime information. Such logged information is valuable for software maintenance. A logging statement usually prints one or more variables to record vital system status. However, due to the lack of rigorous logging guidance and the requirement of domain-specific knowledge, it is not easy for developers to make proper decisions about which variables to log. To address this need, in this work, we propose an approach to recommend logging variables for developers during development by learning from existing logging statements. Different from other prediction tasks in software …
Artificial Intelligence And Work: Two Perspectives, Steven Miller, Thomas H. Davenport
Artificial Intelligence And Work: Two Perspectives, Steven Miller, Thomas H. Davenport
Research Collection School Of Computing and Information Systems
One of the most important issues in contemporary societies is the impact of intelligent technologies on human work. For an empirical perspective on the issue, we recently completed 30 case studies of people collaborating with AI-enabled smart machines. Twenty-four were from North America, mostly in the US. Six were from Southeast Asia, mostly in Singapore. We compare some of our observations to one of the broadest academic examinations of the issue. In particular, we focus on our case study observations with regard to key findings from the MIT Task Force on the Work of the Future report.
A Learning And Optimization Framework For Collaborative Urban Delivery Problems With Alliances, Jingfeng Yang, Hoong Chuin Lau
A Learning And Optimization Framework For Collaborative Urban Delivery Problems With Alliances, Jingfeng Yang, Hoong Chuin Lau
Research Collection School Of Computing and Information Systems
The emergence of e-Commerce imposes a tremendous strain on urban logistics which in turn raises concerns on environmental sustainability if not performed efficiently. While large logistics service providers (LSPs) can perform fulfillment sustainably as they operate extensive logistic networks, last-mile logistics are typically performed by small LSPs who need to form alliances to reduce delivery costs and improve efficiency, and to compete with large players. In this paper, we consider a multi-alliance multi-depot pickup and delivery problem with time windows (MAD-PDPTW) and formulate it as a mixed-integer programming (MIP) model. To cope with large-scale problem instances, we propose a two-stage …
Does Bert Understand Idioms? A Probing-Based Empirical Study Of Bert Encodings Of Idioms, Minghuan Tan, Jing Jiang
Does Bert Understand Idioms? A Probing-Based Empirical Study Of Bert Encodings Of Idioms, Minghuan Tan, Jing Jiang
Research Collection School Of Computing and Information Systems
Understanding idioms is important in NLP. In this paper, we study to what extent pre-trained BERT model can encode the meaning of a potentially idiomatic expression (PIE) in a certain context. We make use of a few existing datasets and perform two probing tasks: PIE usage classification and idiom paraphrase identification. Our experiment results suggest that BERT indeed can separate the literal and idiomatic usages of a PIE with high accuracy. It is also able to encode the idiomatic meaning of a PIE to some extent.
Enhancing Project Based Learning With Unsupervised Learning Of Project Reflections, Hua Leong Fwa
Enhancing Project Based Learning With Unsupervised Learning Of Project Reflections, Hua Leong Fwa
Research Collection School Of Computing and Information Systems
Natural Language Processing (NLP) is an area of research and application that uses computers to analyze human text. It has seen wide adoption within several industries but few studies have investigated it for use in evaluating the effectiveness of educational interventions and pedagogies. Pedagogies such as Project based learning (PBL) centers on learners solving an authentic problem or challenge which leads to knowledge creation and higher engagement. PBL also lends itself well in plugging the gap between what is taught in classrooms and applying the knowledge gained to the real working environment. In this study, we seek to investigate how …
Semi-Supervised Semantic Visualization For Networked Documents, Delvin Ce Zhang, Hady W. Lauw
Semi-Supervised Semantic Visualization For Networked Documents, Delvin Ce Zhang, Hady W. Lauw
Research Collection School Of Computing and Information Systems
Semantic interpretability and visual expressivity are important objectives in exploratory analysis of text. On the one hand, while some documents may have explicit categories, we could develop a better understanding of a corpus by studying its finer-grained structures, which may be latent. By inferring latent topics and discovering keywords associated with each topic, one obtains a semantic interpretation of the corpus. One the other hand, by visualizing documents, latent topics, and category labels on the same plot, one gains a bird’s eye view of the relationships among documents, topics, and various categories. Semantic visualization is a class of methods that …
Routing Policy Choice Prediction In A Stochastic Network: Recursive Model And Solution Algorithm, Tien Mai, Xinlian Yu, Song Gao, Emma Frejinger
Routing Policy Choice Prediction In A Stochastic Network: Recursive Model And Solution Algorithm, Tien Mai, Xinlian Yu, Song Gao, Emma Frejinger
Research Collection School Of Computing and Information Systems
We propose a Recursive Logit (STD-RL) model for routing policy choice in a stochastic time-dependent (STD) network, where a routing policy is a mapping from states to actions on which link to take next, and a state is defined by node, time and information. A routing policy encapsulates travelers’ adaptation to revealed traffic conditions when making route choices. The STD-RL model circumvents choice set generation, a procedure with known issues related to estimation and prediction. In a given state, travelers make their link choice maximizing the sum of the utility of the outgoing link and the expected maximum utility until …
Holistic Prediction For Public Transport Crowd Flows: A Spatio Dynamic Graph Network Approach, Bingjie He, Shukai Li, Chen Zhang, Baihua Zheng, Fugee Tsung
Holistic Prediction For Public Transport Crowd Flows: A Spatio Dynamic Graph Network Approach, Bingjie He, Shukai Li, Chen Zhang, Baihua Zheng, Fugee Tsung
Research Collection School Of Computing and Information Systems
This paper targets at predicting public transport in-out crowd flows of different regions together with transit flows between them in a city. The main challenge is the complex dynamic spatial correlation of crowd flows of different regions and origin-destination (OD) paths. Different from road traffic flows whose spatial correlations mainly depend on geographical distance, public transport crowd flows significantly relate to the region’s functionality and connectivity in the public transport network. Furthermore, influenced by commuters’ time-varying travel patterns, the spatial correlations change over time. Though there exist many works focusing on either predicting in-out flows or OD transit flows of …
Adversarial Attacks And Mitigation For Anomaly Detectors Of Cyber-Physical Systems, Yifan Jia, Jingyi Wang, Christopher M. Poskitt, Sudipta Chattopadhyay, Jun Sun, Yuqi Chen
Adversarial Attacks And Mitigation For Anomaly Detectors Of Cyber-Physical Systems, Yifan Jia, Jingyi Wang, Christopher M. Poskitt, Sudipta Chattopadhyay, Jun Sun, Yuqi Chen
Research Collection School Of Computing and Information Systems
The threats faced by cyber-physical systems (CPSs) in critical infrastructure have motivated research into a multitude of attack detection mechanisms, including anomaly detectors based on neural network models. The effectiveness of anomaly detectors can be assessed by subjecting them to test suites of attacks, but less consideration has been given to adversarial attackers that craft noise specifically designed to deceive them. While successfully applied in domains such as images and audio, adversarial attacks are much harder to implement in CPSs due to the presence of other built-in defence mechanisms such as rule checkers (or invariant checkers). In this work, we …
Precision Public Health Campaign: Delivering Persuasive Messages To Relevant Segments Through Targeted Advertisements On Social Media, Jisun An, Haewoon Kwak, Hanya M. Qureshi, Ingmar Weber
Precision Public Health Campaign: Delivering Persuasive Messages To Relevant Segments Through Targeted Advertisements On Social Media, Jisun An, Haewoon Kwak, Hanya M. Qureshi, Ingmar Weber
Research Collection School Of Computing and Information Systems
Although established marketing techniques have been applied to design more effective health campaigns, more often than not, the same message is broadcasted to large populations, irrespective of unique characteristics. As individual digital device use has increased, so have individual digital footprints, creating potential opportunities for targeted digital health interventions. We propose a novel precision public health campaign framework to structure and standardize the process of designing and delivering tailored health messages to target particular population segments using social media–targeted advertising tools. Our framework consists of five stages: defining a campaign goal, priority audience, and evaluation metrics; splitting the target audience …
Redesigning Patient Flow In Paediatric Eye Clinic For Pandemic Using Simulation, Kar Way Tan, Bee Keow Goh, Aldy Gunawan
Redesigning Patient Flow In Paediatric Eye Clinic For Pandemic Using Simulation, Kar Way Tan, Bee Keow Goh, Aldy Gunawan
Research Collection School Of Computing and Information Systems
This study proposes a systematic approach to the construction of a simulation model to support decision-making concerning the capacity limit and staffing configurations at the paediatric eye clinic in Singapore under the COVID-19 pandemic situation. During the pandemic, the clinic must ensure that the operations are aligned to the safe-distancing regulations put in place by the Ministry of Health while coping with the demand. We developed simulation models to examine the ‘asis’ process and proposed numerous ‘to-be’ processes for new clinic configurations to operate under the pandemic conditions. We combined scenario-thinking and simulation optimization to determine the additional manpower and …
Characterization And Automatic Updates Of Deprecated Machine-Learning Api Usages, Stefanus Agus Haryono, Thung Ferdian, David Lo, Julia Lawall, Lingxiao Jiang
Characterization And Automatic Updates Of Deprecated Machine-Learning Api Usages, Stefanus Agus Haryono, Thung Ferdian, David Lo, Julia Lawall, Lingxiao Jiang
Research Collection School Of Computing and Information Systems
Due to the rise of AI applications, machine learning (ML) libraries, often written in Python, have become far more accessible. ML libraries tend to be updated periodically, which may deprecate existing APIs, making it necessary for application developers to update their usages. In this paper, we build a tool to automate deprecated API usage updates. We first present an empirical study to better understand how updates of deprecated ML API usages in Python can be done. The study involves a dataset of 112 deprecated APIs from Scikit-Learn, TensorFlow, and PyTorch. Guided by the findings of our empirical study, we propose …
Biasheal: On-The-Fly Black-Box Healing Of Bias In Sentiment Analysis Systems, Zhou Yang, Harshit Jain, Jieke Shi, Muhammad Hilmi Asyrofi, David Lo
Biasheal: On-The-Fly Black-Box Healing Of Bias In Sentiment Analysis Systems, Zhou Yang, Harshit Jain, Jieke Shi, Muhammad Hilmi Asyrofi, David Lo
Research Collection School Of Computing and Information Systems
Although Sentiment Analysis (SA) is widely applied in many domains, existing research has revealed that the unfairness in SA systems can be harmful to the welfare of less privileged people. Several works propose pre-processing and in-processing methods to eliminate bias in SA systems, but little attention is paid to utilizing post-processing methods to heal bias. Postprocessing methods are particularly important for systems that use third-party SA services. Systems that use such services have no access to the SA engine or its training data and thus cannot apply pre-processing nor in-processing methods. Therefore, this paper proposes a black-box post-processing method to …
Learning And Evaluating Chinese Idiom Embeddings, Minghuan Tan, Jing Jiang
Learning And Evaluating Chinese Idiom Embeddings, Minghuan Tan, Jing Jiang
Research Collection School Of Computing and Information Systems
We study the task of learning and evaluating Chinese idiom embeddings. We first construct a new evaluation dataset that contains idiom synonyms and antonyms. Observing that existing Chinese word embedding methods may not be suitable for learning idiom embeddings, we further present a BERT-based method that directly learns embedding vectors for individual idioms. We empirically compare representative existing methods and our method. We find that our method substantially outperforms existing methods on the evaluation dataset we have constructed.
Secure And Verifiable Outsourced Data Dimension Reduction On Dynamic Data, Zhenzhu Chen, Anmin Fu, Robert H. Deng, Ximeng Liu, Yang Yang, Yinghui Zhang
Secure And Verifiable Outsourced Data Dimension Reduction On Dynamic Data, Zhenzhu Chen, Anmin Fu, Robert H. Deng, Ximeng Liu, Yang Yang, Yinghui Zhang
Research Collection School Of Computing and Information Systems
Dimensionality reduction aims at reducing redundant information in big data and hence making data analysis more efficient. Resource-constrained enterprises or individuals often outsource this time-consuming job to the cloud for saving storage and computing resources. However, due to inadequate supervision, the privacy and security of outsourced data have been a serious concern to data owners. In this paper, we propose a privacypreserving and verifiable outsourcing scheme for data dimension reduction, based on incremental Non-negative Matrix Factorization (NMF) method. We emphasize the importance of incremental data processing, exploiting the properties of NMF to enable data dynamics in consideration of data updating …
Dynamic Heterogeneous Graph Embedding Via Heterogeneous Hawkes Process, Yugang Ji, Tianrui Jia, Yuan Fang, Chuan Shi
Dynamic Heterogeneous Graph Embedding Via Heterogeneous Hawkes Process, Yugang Ji, Tianrui Jia, Yuan Fang, Chuan Shi
Research Collection School Of Computing and Information Systems
Graph embedding, aiming to learn low-dimensional representations of nodes while preserving valuable structure information, has played a key role in graph analysis and inference. However, most existing methods deal with static homogeneous topologies, while graphs in real-world scenarios are gradually generated with different-typed temporal events, containing abundant semantics and dynamics. Limited work has been done for embedding dynamic heterogeneous graphs since it is very challenging to model the complete formation process of heterogeneous events. In this paper, we propose a novel Heterogeneous Hawkes Process based dynamic Graph Embedding (HPGE) to handle this problem. HPGE effectively integrates the Hawkes process into …
Injecting Descriptive Meta-Information Into Pre-Trained Language Models With Hypernetworks, Wenying Duan, Xiaoxi He, Zimu Zhou, Hong Rao, Lothar Thiele
Injecting Descriptive Meta-Information Into Pre-Trained Language Models With Hypernetworks, Wenying Duan, Xiaoxi He, Zimu Zhou, Hong Rao, Lothar Thiele
Research Collection School Of Computing and Information Systems
Pre-trained language models have been widely adopted as backbones in various natural language processing tasks. However, existing pre-trained language models ignore the descriptive meta-information in the text such as the distinction between the title and the mainbody, leading to over-weighted attention to insignificant text. In this paper, we propose a hypernetwork-based architecture to model the descriptive meta-information and integrate it into pre-trained language models. Evaluations on three natural language processing tasks show that our method notably improves the performance of pre-trained language models and achieves the state-of-the-art results on keyphrase extraction.
The Empathetic Car: Exploring Emotion Inference Via Driver Behaviour And Traffic Context, Shu Liu, Kevin Koch, Zimu Zhou, Simon Foll, Xiaoxi He, Tina Menke, Elgar Fleisch, Felix Wortmann
The Empathetic Car: Exploring Emotion Inference Via Driver Behaviour And Traffic Context, Shu Liu, Kevin Koch, Zimu Zhou, Simon Foll, Xiaoxi He, Tina Menke, Elgar Fleisch, Felix Wortmann
Research Collection School Of Computing and Information Systems
An empathetic car that is capable of reading the driver’s emotions has been envisioned by many car manufacturers. Emotion inference enables in-vehicle applications to improve driver comfort, well-being, and safety. Available emotion inference approaches use physiological, facial, and speech-related data to infer emotions during driving trips. However, existing solutions have two major limitations: Relying on sensors that are not built into the vehicle restricts emotion inference to those people leveraging corresponding devices (e.g., smartwatches). Relying on modalities such as facial expressions and speech raises privacy concerns. By contrast, researchers in mobile health have been able to infer affective states (e.g., …
A Lagrangian Column Generation Approach For The Probabilistic Crowdsourced Logistics Planning, Chung-Kyun Han, Shih-Fen Cheng
A Lagrangian Column Generation Approach For The Probabilistic Crowdsourced Logistics Planning, Chung-Kyun Han, Shih-Fen Cheng
Research Collection School Of Computing and Information Systems
In recent years we have increasingly seen the movement for the retail industry to move their operations online. Along the process, it has created brand new patterns for the fulfillment service, and the logistics service providers serving these retailers have no choice but to adapt. The most challenging issues faced by all logistics service providers are the highly fluctuating demands and the shortening response times. All these challenges imply that maintaining a fixed fleet will either be too costly or insufficient. One potential solution is to tap into the crowdsourced workforce. However, existing industry practices of relying on human planners …
An Empirical Study Of The Discreteness Prior In Low-Rank Matrix Completion, Rodrigo Alves, Antoine Ledent, Renato Assunção, Marius And Kloft
An Empirical Study Of The Discreteness Prior In Low-Rank Matrix Completion, Rodrigo Alves, Antoine Ledent, Renato Assunção, Marius And Kloft
Research Collection School Of Computing and Information Systems
A reasonable assumption in recommender systems is that the rows (users) and columns (items) of the rating matrix can be split into groups (communities) with the following property: each entry of the matrix is the sum of components corresponding to community behavior and a purely low-rank component corresponding to individual behavior. We investigate (1) whether such a structure is present in real-world datasets, (2) whether the knowledge of the existence of such structure alone can improve performance, without explicit information about the community memberships. To these ends, we formulate a joint optimization problem over all (completed matrix, set of communities) …
A Survey On Ml4vis: Applying Machine Learning Advances To Data Visualization, Qianwen Wang, Zhutian Chen, Yong Wang, Huamin Qu
A Survey On Ml4vis: Applying Machine Learning Advances To Data Visualization, Qianwen Wang, Zhutian Chen, Yong Wang, Huamin Qu
Research Collection School Of Computing and Information Systems
Inspired by the great success of machine learning (ML), researchers have applied ML techniques to visualizations to achieve a better design, development, and evaluation of visualizations. This branch of studies, known as ML4VIS, is gaining increasing research attention in recent years. To successfully adapt ML techniques for visualizations, a structured understanding of the integration of ML4VIS is needed. In this article, we systematically survey 88 ML4VIS studies, aiming to answer two motivating questions: “what visualization processes can be assisted by ML?” and “how ML techniques can be used to solve visualization problems? ” This survey reveals seven main processes where …
Learning To Assign: Towards Fair Task Assignment In Large-Scale Ride Hailing, Dingyuan Shi, Yongxin Tong, Zimu Zhou, Bingchen Song, Weifeng Lv, Qiang Yang
Learning To Assign: Towards Fair Task Assignment In Large-Scale Ride Hailing, Dingyuan Shi, Yongxin Tong, Zimu Zhou, Bingchen Song, Weifeng Lv, Qiang Yang
Research Collection School Of Computing and Information Systems
Ride hailing is a widespread shared mobility application where the central issue is to assign taxi requests to drivers with various objectives. Despite extensive research on task assignment in ride hailing, the fairness of earnings among drivers is largely neglected. Pioneer studies on fair task assignment in ride hailing are ineffective and inefficient due to their myopic optimization perspective and timeconsuming assignment techniques. In this work, we propose LAF, an effective and efficient task assignment scheme that optimizes both utility and fairness. We adopt reinforcement learning to make assignments in a holistic manner and propose a set of acceleration techniques …
Boundary Detection With Bert For Span-Level Emotion Cause Analysis, Xiangju Li, Wei Gao, Shi Feng, Yifei Zhang, Daling Wang
Boundary Detection With Bert For Span-Level Emotion Cause Analysis, Xiangju Li, Wei Gao, Shi Feng, Yifei Zhang, Daling Wang
Research Collection School Of Computing and Information Systems
Emotion cause analysis (ECA) has been anemerging topic in natural language processing,which aims to identify the reasons behind acertain emotion expressed in the text. MostECA methods intend to identify the clausewhich contains the cause of a given emotion,but such clause-level ECA (CECA) can be ambiguous and imprecise. In this paper, we aimat span-level ECA (SECA) by detecting theprecise boundaries of text spans conveying accurate emotion causes from the given context.We formulate this task as sequence labelingand position identification problems and design two neural methods to solve them. Experiments on two benchmark ECA datasets showthat the proposed methods substantially outperform the …
Modeling Transitions Of Focal Entities For Conversational Knowledge Base Question Answering, Yunshi Lan, Jing Jiang
Modeling Transitions Of Focal Entities For Conversational Knowledge Base Question Answering, Yunshi Lan, Jing Jiang
Research Collection School Of Computing and Information Systems
Conversational KBQA is about answering a sequence of questions related to a KB. Follow-up questions in conversational KBQA often have missing information referring to entities from the conversation history. In this paper, we propose to model these implied entities, which we refer to as the focal entities of the conversation. We propose a novel graph-based model to capture the transitions of focal entities and apply a graph neural network to derive a probability distribution of focal entities for each question, which is then combined with a standard KBQA module to perform answer ranking. Our experiments on two datasets demonstrate the …
Pruning-Aware Merging For Efficient Multitask Inference, Dawei Gao, Xiaoxi He, Zimu Zhou, Yongxin Tong, Lothar Thiele
Pruning-Aware Merging For Efficient Multitask Inference, Dawei Gao, Xiaoxi He, Zimu Zhou, Yongxin Tong, Lothar Thiele
Research Collection School Of Computing and Information Systems
Many mobile applications demand selective execution of multiple correlated deep learning inference tasks on resource-constrained platforms. Given a set of deep neural networks, each pre-trained for a single task, it is desired that executing arbitrary combinations of tasks yields minimal computation cost. Pruning each network separately yields suboptimal computation cost due to task relatedness. A promising remedy is to merge the networks into a multitask network to eliminate redundancy across tasks before network pruning. However, pruning a multitask network combined by existing network merging schemes cannot minimise the computation cost of every task combination because they do not consider such …
Crossasr++: A Modular Differential Testing Framework For Automatic Speech Recognition, Muhammad Hilmi Asyrofi, Zhou Yang, David Lo
Crossasr++: A Modular Differential Testing Framework For Automatic Speech Recognition, Muhammad Hilmi Asyrofi, Zhou Yang, David Lo
Research Collection School Of Computing and Information Systems
Developers need to perform adequate testing to ensure the quality of Automatic Speech Recognition (ASR) systems. However, manually collecting required test cases is tedious and time-consuming. Our recent work proposes CrossASR, a differential testing method for ASR systems. This method first utilizes Text-to-Speech (TTS) to generate audios from texts automatically and then feed these audios into different ASR systems for cross-referencing to uncover failed test cases. It also leverages a failure estimator to find failing test cases more efficiently. Such a method is inherently self-improvable: the performance can increase by leveraging more advanced TTS and ASR systems. So, in this …
Toward Explainable Deep Anomaly Detection, Guansong Pang, Charu Aggarwal
Toward Explainable Deep Anomaly Detection, Guansong Pang, Charu Aggarwal
Research Collection School Of Computing and Information Systems
Anomaly explanation, also known as anomaly localization, is as important as, if not more than, anomaly detection in many realworld applications. However, it is challenging to build explainable detection models due to the lack of anomaly-supervisory information and the unbounded nature of anomaly; most existing studies exclusively focus on the detection task only, including the recently emerging deep learning-based anomaly detection that leverages neural networks to learn expressive low-dimensional representations or anomaly scores for the detection task. Deep learning models, including deep anomaly detection models, are often constructed as black boxes, which have been criticized for the lack of explainability …