Open Access. Powered by Scholars. Published by Universities.®

Databases and Information Systems Commons™

Open Access. Powered by Scholars. Published by Universities.®

2022

Discipline
Institution
Keyword
Publication
Publication Type

Articles 31 - 60 of 448

Full-Text Articles in Databases and Information Systems

S-Prompts Learning With Pre-Trained Transformers: An Occam's Razor For Domain Incremental Learning, Yabin Wang, Zhiwu Huang, Xiaopeng. Hong Dec 2022

S-Prompts Learning With Pre-Trained Transformers: An Occam's Razor For Domain Incremental Learning, Yabin Wang, Zhiwu Huang, Xiaopeng. Hong

Research Collection School Of Computing and Information Systems

State-of-the-art deep neural networks are still struggling to address the catastrophic forgetting problem in continual learning. In this paper, we propose one simple paradigm (named as S-Prompting) and two concrete approaches to highly reduce the forgetting degree in one of the most typical continual learning scenarios, i.e., domain increment learning (DIL). The key idea of the paradigm is to learn prompts independently across domains with pre-trained transformers, avoiding the use of exemplars that commonly appear in conventional methods. This results in a win-win game where the prompting can achieve the best for each domain. The independent prompting across domains only …

Go to article

Deep Just-In-Time Defect Localization, Fangcheng Qiu, Zhipeng Gao, Xin Xia, David Lo, John Grundy, Xinyu Wang Dec 2022

Deep Just-In-Time Defect Localization, Fangcheng Qiu, Zhipeng Gao, Xin Xia, David Lo, John Grundy, Xinyu Wang

Research Collection School Of Computing and Information Systems

During software development and maintenance, defect localization is an essential part of software quality assurance. Even though different techniques have been proposed for defect localization, i.e., information retrieval (IR)-based techniques and spectrum-based techniques, they can only work after the defect has been exposed, which can be too late and costly to adapt to the newly introduced bugs in the daily development. There are also many JIT defect prediction tools that have been proposed to predict the buggy commit. But these tools do not locate the suspicious buggy positions in the buggy commit. To assist developers to detect bugs in time …

Go to article

Supply Regulation Under The Exclusion Policy In A Ride-Sourcing Market, Xiaonan Li, Xiangyong Li, Hai Wang, Junxin Shi, Yash P. Aneja Dec 2022

Supply Regulation Under The Exclusion Policy In A Ride-Sourcing Market, Xiaonan Li, Xiangyong Li, Hai Wang, Junxin Shi, Yash P. Aneja

Research Collection School Of Computing and Information Systems

On-demand ride-sourcing platforms have quickly emerged and become ubiquitous in our daily lives. Motivated by the rising public concern about service quality in the ride-sourcing market, this paper aims to examine the impact of exclusion policy that can serve as both quality management and supply regulation strategy. With an exclusion policy, the platform excludes low-quality service providers/drivers from the ride-sourcing market by setting a quality threshold of admission (QTA). We propose a model to describe and analyze the market equilibrium under the exclusion policy and present our analytical and numerical results – some of which are non-intuitive and intriguing. Considering …

Go to article

Question-Attentive Review-Level Recommendation Explanation, Trung Hoang Le, Hady Wirawan Lauw Dec 2022

Question-Attentive Review-Level Recommendation Explanation, Trung Hoang Le, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Recommendation explanations help to improve their acceptance by end users. The form of explanation of interest here is presenting an existing review of the recommended item. The challenge is in selecting a suitable review, which is customarily addressed by assessing the relative importance of each review to the recommendation objective. Our focus is on improving review-level explanation by leveraging additional information in the form of questions and answers (QA). The proposed framework employs QA in an attention mechanism that aligns reviews to various QAs of an item and assesses their contribution jointly to the recommendation objective. The benefits are two-fold. …

Go to article

The Rise Of Terrorism In Africa And What It Means For U.S. Policymakers, Bridget Mary Hughes Dec 2022

The Rise Of Terrorism In Africa And What It Means For U.S. Policymakers, Bridget Mary Hughes

Master's Theses

This thesis utilizes three case studies to measure the rise of terrorism in Africa. This qualitative data leads the reader to one ultimate question: what does the rise in terrorism in Africa mean for the United States (U.S.) and U.S. policymakers, National Security academia, students in National Security, if anything at all? The answer is: if civilian and military compounds are being targeted by these violent extremists, as these three case studies demonstrate, it is my recommendation that U.S. policymakers cease sending troops to the African theater and, instead, allocate funding to the citizens and nonprofits of the countries whom …

Go to article

Using Landsat Satellite Imagery To Estimate Groundcover In The Grainbelt Of Western Australia, Justin Laycock, Nick Middleton, Karen Holmes Dec 2022

Using Landsat Satellite Imagery To Estimate Groundcover In The Grainbelt Of Western Australia, Justin Laycock, Nick Middleton, Karen Holmes

Resource management technical reports

Maintaining vegetative groundcover is an important component of sustainable agricultural systems and plays a critical function for soil and land conservation in Western Australia’s (WA) grainbelt (the south-west cropping region). This report describes how satellite imagery can be used to quantitatively and objectively estimate total vegetative groundcover, both in near real time and historically across large areas. We used the Landsat seasonal fractional groundcover products developed by the Joint Remote Sensing Research Program from the extensive archive of Landsat imagery. These products provide an estimate of the percentage of green vegetation, non-green vegetation and bare soil for each 30 m …

Go to article

Pacific: Towards Proactive Conversational Question Answering Over Tabular And Textual Data In Finance, Yang Deng, Wenqiang Lei, Wenxuan Zhang, Wai Lam, Tat-Seng Chua Dec 2022

Pacific: Towards Proactive Conversational Question Answering Over Tabular And Textual Data In Finance, Yang Deng, Wenqiang Lei, Wenxuan Zhang, Wai Lam, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

To facilitate conversational question answering (CQA) over hybrid contexts in finance, we present a new dataset, named PACIFIC. Compared with existing CQA datasets, PACIFIC exhibits three key features: (i) proactivity, (ii) numerical reasoning, and (iii) hybrid context of tables and text. A new task is defined accordingly to study Proactive Conversational Question Answering (PCQA), which combines clarification question generation and CQA. In addition, we propose a novel method, namely UniPCQA, to adapt a hybrid format of input and output content in PCQA into the Seq2Seq problem, including the reformulation of the numerical reasoning process as code generation. UniPCQA performs multi-task …

Go to article

On The Merge Of K-Nn Graph, Wan-Lei Zhao, Hui Wang, Peng-Cheng Lin, Chong-Wah Ngo Dec 2022

On The Merge Of K-Nn Graph, Wan-Lei Zhao, Hui Wang, Peng-Cheng Lin, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

k-nearest neighbor graph is a fundamental data structure in many disciplines such as information retrieval, data-mining, pattern recognition, and machine learning, etc. In the literature, considerable research has been focusing on how to efficiently build an approximate k-nearest neighbor graph (k-NN graph) for a fixed dataset. Unfortunately, a closely related issue of how to merge two existing k-NN graphs has been overlooked. In this paper, we address the issue of k-NN graph merging in two different scenarios. In the first scenario, a symmetric merge algorithm is proposed to combine two approximate k-NN graphs. The algorithm facilitates large-scale processing by the …

Go to article

Implementation Of Empath X Sla Predictive Tool For A Government Agency, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh Dec 2022

Implementation Of Empath X Sla Predictive Tool For A Government Agency, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh

Research Collection School Of Computing and Information Systems

Service Level Agreement (SLA) plays a significant role in the relationship between citizens and the government. It stipulates the quality levels required for the meaningful interaction between the two parties. Most SLA predictive models consider end-to-end duration and frequency of failed service requests as model inputs with little research on the analysis of textual details of the service request. This is an issue for government bodies as the latter do not just want to meet SLA, but also be proactive by knowing the citizens before assisting them. Inclusion of textual data potentially answer to this requirement of knowing the citizen …

Go to article

Appearance-Preserved Portrait-To-Anime Translation Via Proxy-Guided Domain Adaptation, Wenpeng Xiao, Cheng Xu, Jiajie Mai, Xuemiao Xu, Yue Li, Chengze Li, Xueting Liu, Shengfeng He Dec 2022

Appearance-Preserved Portrait-To-Anime Translation Via Proxy-Guided Domain Adaptation, Wenpeng Xiao, Cheng Xu, Jiajie Mai, Xuemiao Xu, Yue Li, Chengze Li, Xueting Liu, Shengfeng He

Research Collection School Of Computing and Information Systems

Converting a human portrait to anime style is a desirable but challenging problem. Existing methods fail to resolve this problem due to the large inherent gap between two domains that cannot be overcome by a simple direct mapping. For this reason, these methods struggle to preserve the appearance features in the original photo. In this paper, we discover an intermediate domain, the coser portrait (portraits of humans costuming as anime characters), that helps bridge this gap. It alleviates the learning ambiguity and loosens the mapping difficulty in a progressive manner. Specifically, we start from learning the mapping between coser and …

Go to article

Segment-Wise Time-Varying Dynamic Bayesian Network With Graph Regularization, Xing Yang, Chen Zhang, Baihua Zheng Dec 2022

Segment-Wise Time-Varying Dynamic Bayesian Network With Graph Regularization, Xing Yang, Chen Zhang, Baihua Zheng

Research Collection School Of Computing and Information Systems

Time-varying dynamic Bayesian network (TVDBN) is essential for describing time-evolving directed conditional dependence structures in complex multivariate systems. In this article, we construct a TVDBN model, together with a score-based method for its structure learning. The model adopts a vector autoregressive (VAR) model to describe inter-slice and intra-slice relations between variables. By allowing VAR parameters to change segment-wisely over time, the time-varying dynamics of the network structure can be described. Furthermore, considering some external information can provide additional similarity information of variables. Graph Laplacian is further imposed to regularize similar nodes to have similar network structures. The regularized maximum a …

Go to article

Cold Calls To Enhance Class Participation And Student Engagement, Manoj Thulasidas, Aldy Gunawan Dec 2022

Cold Calls To Enhance Class Participation And Student Engagement, Manoj Thulasidas, Aldy Gunawan

Research Collection School Of Computing and Information Systems

The question whether cold calls increase student engagement in the classroom has not been conclusively answered in the literature. This study describes the automated system to implement unbiased, randomized cold calling by posing a question, allowing all students to think first and then calling on a particular student to respond. Since we already have a measure of the level of student engagement as the self-reported classparticipation entries from the students, its correlation to cold calling is also further studied. The results show that there is a statistically significant increase in the class participation reported, and therefore in student engagement, in …

Go to article

Gamified Online Industry Learning Platform For Teaching Of Foundational Computing Skills, Yi Meng Lau, Rafael Jose Barros Barrios, Gottipati Swapna, Kyong Jin Shim Dec 2022

Gamified Online Industry Learning Platform For Teaching Of Foundational Computing Skills, Yi Meng Lau, Rafael Jose Barros Barrios, Gottipati Swapna, Kyong Jin Shim

Research Collection School Of Computing and Information Systems

Online industry learning platforms are widely used by organizations for employee training and upskilling. Courses or lessons offered by these platforms can be generic or specific to an enterprise application. The increased demand of new hires to learn these platforms or who are already certified in some of these courses has led universities to look at the opportunities for integrating online industry learning platforms into their curricula. Universities hope to use these platforms to aid students in their learning of concepts and theories. At the same time, these platforms can equip students with industryrecognized certifications or digital badges. This paper …

Go to article

Prompting For Multimodal Hateful Meme Classification, Rui Cao, Roy Ka-Wei Lee, Wen-Haw Chong, Jing Jiang Dec 2022

Prompting For Multimodal Hateful Meme Classification, Rui Cao, Roy Ka-Wei Lee, Wen-Haw Chong, Jing Jiang

Research Collection School Of Computing and Information Systems

Hateful meme classification is a challenging multimodal task that requires complex reasoning and contextual background knowledge. Ideally, we could leverage an explicit external knowledge base to supplement contextual and cultural information in hateful memes. However, there is no known explicit external knowledge base that could provide such hate speech contextual information. To address this gap, we propose PromptHate, a simple yet effective prompt-based model that prompts pre-trained language models (PLMs) for hateful meme classification. Specifically, we construct simple prompts and provide a few in-context examples to exploit the implicit knowledge in the pretrained RoBERTa language model for hateful meme classification. …

Go to article

Bank Error In Whose Favor? A Case Study Of Decentralized Finance Misgovernance, Ping Fan Ke, Ka Chung Boris Ng Dec 2022

Bank Error In Whose Favor? A Case Study Of Decentralized Finance Misgovernance, Ping Fan Ke, Ka Chung Boris Ng

Research Collection School Of Computing and Information Systems

Decentralized Finance (DeFi) emerged rapidly in recent years and provided open and transparent financial services to the public. Due to its popularity, it is not uncommon to see cybersecurity incidents in the DeFi landscape, yet the impact of such incidents is under-studied. In this paper, we examine two incidents in DeFi protocol that are mainly caused by misgovernance and mistake in the smart contract. By using the synthetic control method, we found that the incident in Alchemix did not have a significant effect on the total value locked (TVL) in the protocol, whereas the incident in Compound caused a 6.13% …

Go to article

Assessment Design For Digital Education: An Analytics-Based Authentic Assessment Approach, Lim Ming Soon Tristan, Gottipati Swapna, Michelle L. F. Cheong, Christopher Pang, Jun Wei Ng Dec 2022

Assessment Design For Digital Education: An Analytics-Based Authentic Assessment Approach, Lim Ming Soon Tristan, Gottipati Swapna, Michelle L. F. Cheong, Christopher Pang, Jun Wei Ng

Research Collection School Of Computing and Information Systems

This study looks to identify an assessment design construct that overcomes known issues in authentic assessment design practices in digital education. These include lack of "freedom-of-choice", lack of focus on multimodal nature of the digital process, and shortage of effective feedbacks. This study proposes an authentic assessment, that combines gamification (G) with heutagogy (H) and multimodality (M) of assessments, building upon learning analytics (A), known as GHMA. Proposed assessment design is a skills-oriented game-based assessment approach. Learners can determine their own goals and create individualized multimodal artefacts; receive cognitive challenge through cognitively complex tasks structured in gamified non-linear learning paths; …

Go to article

Mining Competitively-Priced Bundle Configurations, Ezekiel Ong Young, Hady W. Lauw Dec 2022

Mining Competitively-Priced Bundle Configurations, Ezekiel Ong Young, Hady W. Lauw

Research Collection School Of Computing and Information Systems

We examine the bundle configuration problem in the presence of competition. Given a competitor's bundle configuration and pricing, we determine what to bundle together, and at what prices, to maximize the target firm's revenue. We highlight the difficulty in pricing bundles and propose a scalable alternative and an efficient search heuristic to refine the approximate prices. Furthermore, we extend the heuristics proposed by previous work to accommodate the presence of a competitor. We analyze the effectiveness of our proposed models through experimentation on real-life ratings-based preference data.

Go to article

Singlish Checker: A Tool For Understanding And Analysing An English Creole Language, Lee-Hsun Hsieh, Nam Chew Chua, Agus Trisnajaya Kwee, Pei-Chi Lo, Yang-Yin Lee, Ee-Peng Lim Dec 2022

Singlish Checker: A Tool For Understanding And Analysing An English Creole Language, Lee-Hsun Hsieh, Nam Chew Chua, Agus Trisnajaya Kwee, Pei-Chi Lo, Yang-Yin Lee, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

As English is a widely used language in many countries of different cultures, variants of English also known as English creoles have also been created. Singlish is one such English creole used by people in Singapore. Nevertheless, unlike English, Singlish is not taught in schools nor encouraged to be used in formal communications. Hence, it remains to be a low resource language with a lack of up-to-date Singlish word dictionary and computational tools to analyse the language. In this paper, we therefore propose Singlish Checker, a tool that is able to help detecting Singlish text, Singlish words and phrases. To …

Go to article

On The Robustness Of Diffusion In A Network Under Node Attacks, Alvis Logins, Yuchen Li, Panagiotis Karras Dec 2022

On The Robustness Of Diffusion In A Network Under Node Attacks, Alvis Logins, Yuchen Li, Panagiotis Karras

Research Collection School Of Computing and Information Systems

How can we assess a network's ability to maintain its functionality under attacks Network robustness has been studied extensively in the case of deterministic networks. However, applications such as online information diffusion and the behavior of networked public raise a question of robustness in probabilistic networks. We propose three novel robustness measures for networks hosting a diffusion under the Independent Cascade or Linear Threshold model, susceptible to attacks by an adversarial attacker who disables nodes. The outcome of such a process depends on the selection of its initiators, or seeds, by the seeder, as well as on two factors outside …

Go to article

Advancing Statistical Learning And Decision Modeling Using Irregularly-Sampled Multivariate Data For Managing Respiratory Diseases, Maryam Alimohammadi Dec 2022

Advancing Statistical Learning And Decision Modeling Using Irregularly-Sampled Multivariate Data For Managing Respiratory Diseases, Maryam Alimohammadi

Graduate Theses and Dissertations

Complex healthcare systems require efficient and effective data-driven decision making in various aspects. As patient data becomes more available, advanced statistical learning and machine learning techniques are applied to improve data-driven decision making. However, patient health data, including clinical trial data, medical records, and electronic health records, are associated with several challenges. Patient health data includes medical information of a patient that may includedemographics, information relating to their health or illness, medications and treatments, etc. They are a combination of static and time series variables, with many censoring and missingness in the data, and are irregularly sampled in most cases. …

Go to article

Learning Generalizable Models For Vehicle Routing Problems Via Knowledge Distillation, Jieyi Bi, Yining Ma, Jiahai Wang, Zhiguang Cao, Jinbiao Chen, Yuan Sun, Yeow Meng Chee Dec 2022

Learning Generalizable Models For Vehicle Routing Problems Via Knowledge Distillation, Jieyi Bi, Yining Ma, Jiahai Wang, Zhiguang Cao, Jinbiao Chen, Yuan Sun, Yeow Meng Chee

Research Collection School Of Computing and Information Systems

Recent neural methods for vehicle routing problems always train and test the deep models on the same instance distribution (i.e., uniform). To tackle the consequent cross-distribution generalization concerns, we bring the knowledge distillation to this field and propose an Adaptive Multi-Distribution Knowledge Distillation (AMDKD) scheme for learning more generalizable deep models. Particularly, our AMDKD leverages various knowledge from multiple teachers trained on exemplar distributions to yield a light-weight yet generalist student model. Meanwhile, we equip AMDKD with an adaptive strategy that allows the student to concentrate on difficult distributions, so as to absorb hard-to-master knowledge more effectively. Extensive experimental results …

Go to article

Learning Dynamic Multimodal Implicit And Explicit Networks For Multiple Financial Tasks, Meng Kiat Gary Ang, Ee-Peng Lim Dec 2022

Learning Dynamic Multimodal Implicit And Explicit Networks For Multiple Financial Tasks, Meng Kiat Gary Ang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Many financial f orecasting d eep l earning w orks focus on the single task of predicting stock returns for trading with unimodal numerical inputs. Investment and risk management however involves multiple financial t asks - f orecasts o f expected returns, risks and correlations of multiple stocks in portfolios, as well as important events affecting different stocks - to support decision making. Moreover, stock returns are influenced by large volumes of non-stationary time-series information from a variety of modalities and the propagation of such information across inter-company relationship networks. Such networks could be explicit - observed co-occurrences in online …

Go to article

R2f: A General Retrieval, Reading And Fusion Framework For Document-Level Natural Language Inference, Hao Wang, Yixin Cao, Yangguang Li, Zhen Huang, Kun Wang, Jing Shao Dec 2022

R2f: A General Retrieval, Reading And Fusion Framework For Document-Level Natural Language Inference, Hao Wang, Yixin Cao, Yangguang Li, Zhen Huang, Kun Wang, Jing Shao

Research Collection School Of Computing and Information Systems

Document-level natural language inference (DocNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents. Current datasets and baselines largely follow sentence-level settings, but fail to address the issues raised by longer documents. In this paper, we establish a general solution, named Retrieval, Reading and Fusion (R2F) framework, and a new setting, by analyzing the main challenges of DocNLI: interpretability, long-range dependency, and cross-sentence inference. The basic idea of the framework is to simplify document-level task into a set of sentence-level tasks, and improve both performance and …

Go to article

Mitigating Popularity Bias In Recommendation With Unbalanced Interactions: A Gradient Perspective, Weijieying Ren, Lei Wang, Kunpeng Liu, Ruocheng Guo, Ee-Peng Lim, Yanjie Fu Dec 2022

Mitigating Popularity Bias In Recommendation With Unbalanced Interactions: A Gradient Perspective, Weijieying Ren, Lei Wang, Kunpeng Liu, Ruocheng Guo, Ee-Peng Lim, Yanjie Fu

Research Collection School Of Computing and Information Systems

Recommender systems learn from historical user-item interactions to identify preferred items for target users. These observed interactions are usually unbalanced following a long-tailed distribution. Such long-tailed data lead to popularity bias to recommend popular but not personalized items to users. We present a gradient perspective to understand two negative impacts of popularity bias in recommendation model optimization: (i) the gradient direction of popular item embeddings is closer to that of positive interactions, and (ii) the magnitude of positive gradient for popular items are much greater than that of unpopular items. To address these issues, we propose a simple yet efficient …

Go to article

Conversation Disentanglement With Bi-Level Contrastive Learning, Chengyu Huang, Zheng Zhang, Hao Fei, Lizi Liao Dec 2022

Conversation Disentanglement With Bi-Level Contrastive Learning, Chengyu Huang, Zheng Zhang, Hao Fei, Lizi Liao

Research Collection School Of Computing and Information Systems

Conversation disentanglement aims to group utterances into detached sessions, which is a fundamental task in processing multi-party conversations. Existing methods have two main drawbacks. First, they overemphasize pairwise utterance relations but pay inadequate attention to the utterance-to-context relation modeling. Second, a huge amount of human annotated data is required for training, which is expensive to obtain in practice. To address these issues, we propose a general disentangle model based on bi-level contrastive learning. It brings closer utterances in the same session while encourages each utterance to be near its clustered session prototypes in the representation space. Unlike existing approaches, our …

Go to article

Innovative And Effective Spreadsheet Tool For Learning Sentiment Analysis And Prediction, Michelle L. F. Cheong, Jean Yun-Chen Chen Dec 2022

Innovative And Effective Spreadsheet Tool For Learning Sentiment Analysis And Prediction, Michelle L. F. Cheong, Jean Yun-Chen Chen

Research Collection School Of Computing and Information Systems

In this paper, we describe a spreadsheet tool which was developed and implemented to teach sentiment analysis and prediction to university students who are less technically inclined. We adopted the “Use-Modify-Create” cycle to ensure that the students learn the computing concepts and practices in a progressive and active learning manner, and we evaluated the effectiveness of the tool using the Learning Object Evaluation Scale for Students (LOES-S). The evaluation shows that our tool performed well in terms of quality, learn and engagement constructs, and our paired T-test shows strong evidence that, on average, the course module with the tool does …

Go to article

What Should Streamers Communicate In Livestream E-Commerce? The Effects Of Social Interactions On Live Streaming Performance, Danyang Song, Xi Chen, Zhiling Guo, Xiao Liu Liu, Ruijin. Jin Dec 2022

What Should Streamers Communicate In Livestream E-Commerce? The Effects Of Social Interactions On Live Streaming Performance, Danyang Song, Xi Chen, Zhiling Guo, Xiao Liu Liu, Ruijin. Jin

Research Collection School Of Computing and Information Systems

Compared with traditional e-commerce, livestreaming e-commerce is characterized by direct and intimate communication between streamers and consumers that stimulates instant social interactions. This study focuses on streamers’ three types of information exchange (i.e., product information, social conversation, and social solicitation) and examines their roles in driving both short-term and long-term livestreaming performance (i.e., sales and customer base growth). We find that the informational role of product information (nonpromotional and promotional) is beneficial not only to sales performance, but also to the growth of the customer base. We also find that social conversation has a relationship-building effect that positively impacts both …

Go to article

Dialogconv: A Lightweight Fully Convolutional Network For Multi-View Response Selection, Yongkang Liu, Shi Feng, Wei Gao, Daling Wang, Yifei Zhang Dec 2022

Dialogconv: A Lightweight Fully Convolutional Network For Multi-View Response Selection, Yongkang Liu, Shi Feng, Wei Gao, Daling Wang, Yifei Zhang

Research Collection School Of Computing and Information Systems

Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms. Although promising results have been achieved, these models often suffer from slow inference or huge number of parameters. In this paper, we propose a novel lightweight fully convolutional architecture, called DialogConv, for response selection. DialogConv is exclusively built on top of convolution to extract matching features of context and response. Dialogues are modeled in 3D views, where DialogConv performs convolution operations on embedding view, word view and utterance view to capture richer semantic information from multiple contextual views. On the four benchmark datasets, …

Go to article

Curiosity-Driven And Victim-Aware Adversarial Policies, Chen Gong, Zhou Yang, Yunpeng Bai, Jieke Shi, Arunesh Sinha, Bowen Xu, David Lo, Xinwen Hou, Guoliang Fan Dec 2022

Curiosity-Driven And Victim-Aware Adversarial Policies, Chen Gong, Zhou Yang, Yunpeng Bai, Jieke Shi, Arunesh Sinha, Bowen Xu, David Lo, Xinwen Hou, Guoliang Fan

Research Collection School Of Computing and Information Systems

Recent years have witnessed great potential in applying Deep Reinforcement Learning (DRL) in various challenging applications, such as autonomous driving, nuclear fusion control, complex game playing, etc. However, recently researchers have revealed that deep reinforcement learning models are vulnerable to adversarial attacks: malicious attackers can train adversarial policies to tamper with the observations of a well-trained victim agent, the latter of which fails dramatically when faced with such an attack. Understanding and improving the adversarial robustness of deep reinforcement learning is of great importance in enhancing the quality and reliability of a wide range of DRL-enabled systems. In this paper, …

Go to article

A Unified Dialogue User Simulator For Few-Shot Data Augmentation, Dazhen Wan, Zheng Zhang, Qi Zhu, Lizi Liao, Minlie Huang Dec 2022

A Unified Dialogue User Simulator For Few-Shot Data Augmentation, Dazhen Wan, Zheng Zhang, Qi Zhu, Lizi Liao, Minlie Huang

Research Collection School Of Computing and Information Systems

Pre-trained language models have shown superior performance in task-oriented dialogues. However, existing datasets are on limited scales, which cannot support large-scale pre-training. Fortunately, various data augmentation methods have been developed to augment largescale task-oriented dialogue corpora. However, they heavily rely on annotated data in the target domain, which require a tremendous amount of data collection and human labeling work. In this paper, we build a unified dialogue user simulation model by pre-training on several publicly available datasets. The model can then be tuned on a target domain with fewshot data. The experiments on a target dataset across multiple domains show …

Go to article

First Prev Next Last