Digital Commons Network^™

Large-Scale Correlation Analysis Of Automated Metrics For Topic Models, Jia Peng Lim, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Automated coherence metrics constitute an important and popular way to evaluate topic models. Previous works present a mixed picture of their presumed correlation with human judgement. In this paper, we conduct a large-scale correlation analysis of coherence metrics. We propose a novel sampling approach to mine topics for the purpose of metric evaluation, and conduct the analysis via three large corpora showing that certain automated coherence metrics are correlated. Moreover, we extend the analysis to measure topical differences between corpora. Lastly, we examine the reliability of human judgement by conducting an extensive user study, which is designed as an amalgamation …

Diaasq: A Benchmark Of Conversational Aspect-Based Sentiment Quadruple Analysis, Bobo Li, Hao Fei, Fei Li, Yuhan Wu, Jinsong Zhang, Shengqiong Wu, Jingye Li, Yijiang Liu, Lizi Liao, Tat-Seng Chua, Donghong Ji

Research Collection School Of Computing and Information Systems

The rapid development of aspect-based sentiment analysis (ABSA) within recent decades shows great potential for real-world society. The current ABSA works, however, are mostly limited to the scenario of a single text piece, leaving the study in dialogue contexts unexplored. To bridge the gap between fine-grained sentiment analysis and conversational opinion mining, in this work, we introduce a novel task of conversational aspect-based sentiment quadruple analysis, namely DiaASQ, aiming to detect the quadruple of target-aspect-opinion-sentiment in a dialogue. We manually construct a large-scale high-quality DiaASQ dataset in both Chinese and English languages. We deliberately develop a neural model to benchmark …

Multi-Target Backdoor Attacks For Code Pre-Trained Models, Yanzhou Li, Shangqing Liu, Kangjie Chen, Xiaofei Xie, Tianwei Zhang, Yang Liu

Research Collection School Of Computing and Information Systems

Backdoor attacks for neural code models have gained considerable attention due to the advancement of code intelligence. However, most existing works insert triggers into task-specific data for code-related downstream tasks, thereby limiting the scope of attacks. Moreover, the majority of attacks for pre-trained models are designed for understanding tasks. In this paper, we propose task-agnostic backdoor attacks for code pre-trained models. Our backdoored model is pre-trained with two learning strategies (i.e., Poisoned Seq2Seq learning and token representation learning) to support the multi-target attack of downstream code understanding and generation tasks. During the deployment phase, the implanted backdoors in the victim …

Augmenting Low-Resource Text Classification With Graph-Grounded Pre-Training And Prompting, Zhihao Wen, Yuan Fang

Research Collection School Of Computing and Information Systems

ext classification is a fundamental problem in information retrieval with many real-world applications, such as predicting the topics of online articles and the categories of e-commerce product descriptions. However, low-resource text classification, with few or no labeled samples, poses a serious concern for supervised learning. Meanwhile, many text data are inherently grounded on a network structure, such as a hyperlink/citation network for online articles, and a user-item purchase network for e-commerce products. These graph structures capture rich semantic relationships, which can potentially augment low-resource text classification. In this paper, we propose a novel model called Graph-Grounded Pre-training and Prompting (G2P2) …

Information Screening Whilst Exploiting! Multimodal Relation Extraction With Feature Denoising And Multimodal Topic Modeling, Shengqiong Wu, Hao Fei, Yixin Cao, Lidong Bing, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Existing research on multimodal relation extraction (MRE) faces two co-existing challenges, internal-information over-utilization and external-information under-exploitation. To combat that, we propose a novel framework that simultaneously implements the idea of internal-information screening and external-information exploiting. First, we represent the fine-grained semantic structures of the input image and text with the visual and textual scene graphs, which are further fused into a unified cross-modal graph (CMG). Based on CMG, we perform structure refinement with the guidance of the graph information bottleneck principle, actively denoising the less-informative features. Next, we perform topic modeling over the input image and text, incorporating latent multimodal …

Cone: An Efficient Coarse-To-Fine Alignment Framework For Long Video Temporal Grounding, Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, Wing-Kwong Chan, Chong-Wah Ngo, Mike Z. Shou, Nan. Duan

Research Collection School Of Computing and Information Systems

This paper tackles an emerging and challenging problem of long video temporal grounding (VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less explored, which brings new challenges in higher inference computation cost and weaker multi-modal alignment. To address these challenges, we propose CONE, an efficient COarse-to-fiNE alignment framework. CONE is a plug-and-play framework on top of existing VTG models to handle long videos through a sliding window mechanism. Specifically, CONE (1) introduces a query-guided window selection strategy to speed up inference, and (2) proposes a …

Prompt To Be Consistent Is Better Than Self-Consistent? Few-Shot And Zero-Shot Fact Verification With Pre-Trained Language Models, Fengzhu Zeng, Wei Gao

Research Collection School Of Computing and Information Systems

Few-shot or zero-shot fact verification only relies on a few or no labeled training examples. In this paper, we propose a novel method called ProToCo, to Prompt pre-trained language models (PLMs) To be Consistent, for improving the factuality assessment capability of PLMs in the few-shot and zero-shot settings. Given a claim-evidence pair, ProToCo generates multiple variants of the claim with different relations and frames a simple consistency mechanism as constraints for making compatible predictions across these variants. We update PLMs by using parameter-efficient fine-tuning (PEFT), leading to more accurate predictions in few-shot and zero-shot fact verification tasks. Our experiments on …

Multi-View Hypergraph Contrastive Policy Learning For Conversational Recommendation, Sen Zhao, Wei Wei, Xian-Ling Mao, Shuai: Yang Zhu, Zujie Wen, Dangyang Chen, Feida Zhu, Feida Zhu

Research Collection School Of Computing and Information Systems

Conversational recommendation systems (CRS) aim to interactively acquire user preferences and accordingly recommend items to users. Accurately learning the dynamic user preferences is of crucial importance for CRS. Previous works learn the user preferences with pairwise relations from the interactive conversation and item knowledge, while largely ignoring the fact that factors for a relationship in CRS are multiplex. Specifically, the user likes/dislikes the items that satisfy some attributes (Like/Dislike view). Moreover social influence is another important factor that affects user preference towards the item (Social view), while is largely ignored by previous works in CRS. The user preferences from these …

Generative Ai And Chatgpt: Applications, Challenges, And Ai-Human Collaboration, Fiona Nah, Ruilin Zheng, Jingyuan Cai, Keng Siau, Langtao Chen

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI) has elicited much attention across disciplines and industries (Hyder et al., Citation2019). AI has been defined as “a system’s ability to correctly interpret external data, to learn from such data, and to use those learnings to achieve specific goals and tasks through flexible adaptation” (Kaplan & Haenlein, Citation2019, p. 15). AI has gone through several development stages and AI winters. In the first two decades (i.e., 1950s and 1960s), AI demonstrated success which included programs such as General Problem Solver (Newell et al., Citation1959) and ELIZA (Weizenbaum, Citation1966). However, limitations in processing capacity and reduced spending on …

Augmenting Fake Content Detection In Online Platforms: A Domain Adaptive Transfer Learning Via Adversarial Training Approach, Ka Chung Ng, Ping Fan Ke, Mike K. P. So, Kar Yan Tam

Research Collection School Of Computing and Information Systems

Online platforms are experimenting with interventions such as content screening to moderate the effects of fake, biased, and incensing content. Yet, online platforms face an operational challenge in implementing machine learning algorithms for managing online content due to the labeling problem, where labeled data used for model training are limited and costly to obtain. To address this issue, we propose a domain adaptive transfer learning via adversarial training approach to augment fake content detection with collective human intelligence. We first start with a source domain dataset containing deceptive and trustworthy general news constructed from a large collection of labeled news …

Knowledge-Enhanced Mixed-Initiative Dialogue System For Emotional Support Conversations, Yang Deng, Wenxuan Zhang, Yifei Yuan, Wai Lam

Research Collection School Of Computing and Information Systems

Unlike empathetic dialogues, the system in emotional support conversations (ESC) is expected to not only convey empathy for comforting the help-seeker, but also proactively assist in exploring and addressing their problems during the conversation. In this work, we study the problem of mixed-initiative ESC where the user and system can both take the initiative in leading the conversation. Specifically, we conduct a novel analysis on mixed-initiative ESC systems with a tailor-designed schema that divides utterances into different types with speaker roles and initiative types. Four emotional support metrics are proposed to evaluate the mixed-initiative interactions. The analysis reveals the necessity …

Towards Robust Personalized Dialogue Generation Via Order-Insensitive Representation Regularization, Liang Chen, Hongru Wang, Yang Deng, Wai-Chung Kwan, Zezhong Wang, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

Generating persona consistent dialogue response is important for developing an intelligent conversational agent. Recent works typically fine-tune large-scale pre-trained models on this task by concatenating persona texts and dialogue history as a single input sequence to generate the target response. While simple and effective, our analysis shows that this popular practice is seriously affected by order sensitivity where different input orders of persona sentences significantly impact the quality and consistency of generated response, resulting in severe performance fluctuations (i.e., 29.4% on GPT2 and 83.2% on BART). To mitigate the order sensitivity problem, we propose a model-agnostic framework, ORder Insensitive Generation …

Product Question Answering In E-Commerce: A Survey, Yang Deng, Wenxuan Zhang, Qian Yu, Wai Lam

Research Collection School Of Computing and Information Systems

Product question answering (PQA), aiming to automatically provide instant responses to customer’s questions in E-Commerce platforms, has drawn increasing attention in recent years. Compared with typical QA problems, PQA exhibits unique challenges such as the subjectivity and reliability of user-generated contents in E-commerce platforms. Therefore, various problem settings and novel methods have been proposed to capture these special characteristics. In this paper, we aim to systematically review existing research efforts on PQA. Specifically, we categorize PQA studies into four problem settings in terms of the form of provided answers. We analyze the pros and cons, as well as present existing …

Goal Awareness For Conversational Ai: Proactivity, Non-Collaborativity, And Beyond, Yang Deng, Wenqiang Lei, Minlie Huang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Conversational systems are envisioned to provide social support or functional service to human users via natural language interactions. Conventional conversation researches mainly focus on the responseability of the system, such as dialogue context understanding and response generation, but overlooks the design of an essential property in intelligent conversations, i.e., goal awareness. The awareness of goals means the state of not only being responsive to the users but also aware of the target conversational goal and capable of leading the conversation towards the goal, which is a significant step towards higher-level intelligence and artificial consciousness. It can not only largely improve …

Strategy‑Aware Bundle Recommender System, Yinwei Wei, Xiaohao Liu, Yunshan Ma, Xiang Wang, Liqiang Nie, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

A bundle is a group of items that provides improved services to users and increased profits for sellers. However, locating the desired bundles that match the users' tastes still challenges us, due to the sparsity issue. Despite the remarkable performance of existing approaches, we argue that they seldom consider the bundling strategy (i.e., how the items within a bundle are associated with each other) in the bundle recommendation, resulting in the suboptimal user and bundle representations for their interaction prediction. Therefore, we propose to model the strategy-aware user and bundle representations for the bundle recommendation.Towards this end, we develop a …

The Interactive Effects Of Societal And Organizational Cultural Tightness On Employee Work Related Outcomes, Na Zhao

Dissertations and Theses Collection (Open Access)

Individuals are shaped by both their organizational and societal cultures, yet existing research often approaches these cultural dimensions in isolation, ignoring their combined impact on individual behaviors. In response to this research gap, I developed a novel theoretical framework by combining cultural tightness literature with social information processing theory. This framework highlights the interactive impacts of societal and organizational cultures on employees’ outcomes, including job performance, work attitudes, and mental health. Moreover, I proposed several mechanisms, including motivational, cognitive, and emotional mechanisms, through which these forms of cultural tightness could shape these specified work-related outcomes. To validate this framework, I …

Essays On Corporate Social Responsibility And Strategic Choices, Yah Ling Liew

Dissertations and Theses Collection (Open Access)

CSR is receiving significant attention from both academics and businesses. However, CSR and economic goals are still perceived as conflicting. To address this gap, this dissertation put together three essays that to inform about the instrumental value of CSR and how CSR could be compatible with economic objectives.

Chapter Two reveals CSR reporting has strategic value for firms by improving firms' relationships with stakeholders and facilitating the development of sustainable development capabilities. Firms are responsive to shareholders' and governments' demands for reporting. As society increasingly demands for CSR reporting, the overlooked issue of costs and benefits of reporting is costly …

Measuring The Learning Effectiveness Of Two Courses In A Program In Accounting Data And Analytics, Clarence Goh, Duan Ning, Magdeleine Lew, Gary Pan, Poh Sun Seow

Research Collection School Of Accountancy

Driven by rapid technological innovation, information technology (IT) is expected to significantly alter the way that accountants work. However, both accounting researchers and practitioners have observed a shortage of accounting professionals who currently possess the relevant technology skillsets to exploit technological advances. In response, the School of Accountancy of a Singapore-based university launched a second major program in Accounting Data and Analytics in 2018. In this study, we examine the learning effectiveness of two courses – Business Data Management and Data Modelling & Visualization – offered as part of the program. Overall, our results suggest that the courses are effective …

Automatic Scoring Of Speeded Interpersonal Assessment Center Exercises Via Machine Learning: Initial Psychometric Evidence And Practical Guidelines, Louis Hickman, Christoph N. Herde, Filip Lievens, Louis Tay

Research Collection Lee Kong Chian School Of Business

Assessment center (AC) exercises such as role-plays have established themselves as valuable approaches for obtaining insights into interpersonal behavior, but they are often considered the “Rolls Royce” of personnel assessment due to their high costs. The observation and rating process comprises a substantial part of these costs. In an exploratory case study, we capitalize on recent advances in natural language processing (NLP) by developing NLP-based machine learning (ML) models to investigate the possibility of automatically scoring AC exercises. First, we compared the convergent-related validity and contamination with word count of ML scores based on models that used different NLP methods …

Regional Human Rights Courts And Specialised Treaty Mechanisms For Investor-State Dispute Resolution, N. Jansen Calamita, Stefanie Schacherer, Facundo Perez-Aznar, Aikaterini Florou

Research Collection Yong Pung How School Of Law

The purpose of the present report is to provide an overview and analysis of the measures that States adopt internally to implement treaties establishing international court and tribunals and other international dispute settlement mechanisms (“IDSM treaties”). Although this report cannot be comprehensive in its survey of practices across all States, this analysis is intended to be useful in three ways. First, it can be useful with respect to the design and drafting of an instrument establishing a multilateral investment dispute settlement mechanism. Second, it can be useful for States when considering what types of implementing measures they may need to …

Position-Guided Text Prompt For Vision-Language Pre-Training, Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou, Yan Shuicheng

Research Collection School Of Computing and Information Systems

Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into N x N blocks, and identifies the objects in each block through the widely used object detector in VLP. It then reformulates …

Multi-Head Attention Graph Convolutional Network Model: End-To-End Entity And Relation Joint Extraction Based On Multi-Head Attention Graph Convolutional Network, Zhihua Tao, Chunping Ouyang, Yongbin Liu, Tonglee Chung, Yixin Cao

Research Collection School Of Computing and Information Systems

At present, the entity and relation joint extraction task has attracted more and more scholars' attention in the field of natural language processing (NLP). However, most of their methods rely on NLP tools to construct dependency trees to obtain sentence structure information. The adjacency matrix constructed by the dependency tree can convey syntactic information. Dependency trees obtained through NLP tools are too dependent on the tools and may not be very accurate in contextual semantic description. At the same time, a large amount of irrelevant information will cause redundancy. This paper presents a novel end-to-end entity and relation joint extraction …

Automating Arduino Programming: From Hardware Setups To Sample Source Code Generation, Imam Nur Bani Yusuf, Diyanah Binte Abdul Jamal, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

An embedded system is a system consisting of software code, controller hardware, and I/O (Input/Output) hardware that performs a specific task. Developing an embedded system presents several challenges. First, the development often involves configuring hardware that requires domain-specific knowledge. Second, the library for the hardware may have API usage patterns that must be followed. To overcome such challenges, we propose a framework called ArduinoProg towards the automatic generation of Arduino applications. ArduinoProg takes a natural language query as input and outputs the configuration and API usage pattern for the hardware described in the query. Motivated by our findings on the …

A Study Of Variable-Role-Based Feature Enrichment In Neural Models Of Code, Aftab. Hussain, Md. Rafiqul Islam. Rabin, Bowen. Xu, David Lo, Mohammad Amin. Alipour

Research Collection School Of Computing and Information Systems

Although deep neural models substantially reduce the overhead of feature engineering, the features readily available in the inputs might significantly impact training cost and the performance of the models. In this paper, we explore the impact of an unsuperivsed feature enrichment approach based on variable roles on the performance of neural models of code. The notion of variable roles (as introduced in the works of Sajaniemi et al. [1], [2]) has been found to help students' abilities in programming. In this paper, we investigate if this notion would improve the performance of neural models of code. To the best of …

Navigating Complexity In Software Engineering: A Prototype For Comparing Gpt-N Solutions, Christoph Treude

Research Collection School Of Computing and Information Systems

Navigating the diverse solution spaces of non-trivial software engineering tasks requires a combination of technical knowledge, problem-solving skills, and creativity. With multiple possible solutions available, each with its own set of trade-offs, it is essential for programmers to evaluate the various options and select the one that best suits the specific requirements and constraints of a project. Whether it is choosing from a range of libraries, weighing the pros and cons of different architecture and design solutions, or finding unique ways to fulfill user requirements, the ability to think creatively is crucial for making informed decisions that will result in …

Win: Weight-Decay-Integrated Nesterov Acceleration For Adaptive Gradient Algorithms, Pan Zhou, Xingyu Xie, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Training deep networks on large-scale datasets is computationally challenging. In this work, we explore the problem of “how to accelerate adaptive gradient algorithms in a general manner”, and aim to provide practical efficiency-boosting insights. To this end, we propose an effective and general Weight-decay-Integrated Nesterov acceleration (Win) to accelerate adaptive algorithms. Taking AdamW and Adam as examples, we minimize a dynamical loss per iteration which combines the vanilla training loss and a dynamic regularizer inspired by proximal point method (PPM) to improve the convexity of the problem. To introduce Nesterov-alike-acceleration into AdamW and Adam, we respectively use the first- and …

Bilingual Profiles Differentially Predict Executive Functions During Early Childhood: A Latent Profile Analysis, Hwajin Yang, Germaine Y. Q. Tng, Wee Qin Ng, Sujin Yang

Research Collection School of Social Sciences

Recent studies suggest that heterogeneous bilingual experiences implicate different executive functions (EF) in children. Using a latent profile analysis, we conducted a more nuanced investigation of multifaceted bilingual experiences. By concurrently considering numerous bilingual indicators – age of L1 and L2 acquisition, interactional contexts of verbal exchanges, L1 and L2 proficiency, balance of language use at home and school, and receptive vocabulary – we identified three latent profiles (subgroups): balanced dual-language, dominant single-language, and mixed-interaction. We found that the balanced dual-language and dominant single-language profiles predicted significantly better switching than the mixed-interaction profile. However, no profile differences were found in …

Contrabert: Enhancing Code Pre-Trained Models Via Contrastive Learning, Shangqing Liu, Bozhi Wu, Xiaofei Xie, Guozhu Meng, Yang. Liu

Research Collection School Of Computing and Information Systems

Large-scale pre-trained models such as CodeBERT, GraphCodeBERT have earned widespread attention from both academia and industry. Attributed to the superior ability in code representation, they have been further applied in multiple downstream tasks such as clone detection, code search and code translation. However, it is also observed that these state-of-the-art pre-trained models are susceptible to adversarial attacks. The performance of these pre-trained models drops significantly with simple perturbations such as renaming variable names. This weakness may be inherited by their downstream models and thereby amplified at an unprecedented scale. To this end, we propose an approach namely ContraBERT that aims …

Wearing Masks Implies Refuting Trump?: Towards Target-Specific User Stance Prediction Across Events In Covid-19 And Us Election 2020, Hong Zhang, Haewoon Kwak, Wei Gao, Jisun An

Research Collection School Of Computing and Information Systems

People who share similar opinions towards controversial topics could form an echo chamber and may share similar political views toward other topics as well. The existence of such connections, which we call connected behavior, gives researchers a unique opportunity to predict how one would behave for a future event given their past behaviors. In this work, we propose a framework to conduct connected behavior analysis. Neural stance detection models are trained on Twitter data collected on three seemingly independent topics, i.e., wearing a mask, racial equality, and Trump, to detect people’s stance, which we consider as their online behavior in …

Teaching In The Right Context: Textbook Supply Program, Language, And Vocabulary Ability In Vietnam, Tomoki Fujii, Maki Nakajima, Sijia Xu

Research Collection School Of Economics

An ethnic gap in education is prevalent around the world. This remains the case in Vietnam, a country that has achieved phenomenal economic growth and raised the educational attainment of the public. This paper examines the impact of language policy reorientation represented by the textbook supply program in Vietnam on the ethnic gap in children's learning measured by a vocabulary test. Applying difference-in-differences estimation to the Young Lives data between 2006 and 2015, we show that the program became more effective in narrowing the ethnic gap as the education policy became reoriented toward ethnic minority children. A causal mediation analysis …