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

Digital Commons Network™

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

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 601 - 630 of 1692

Full-Text Articles in Entire DC Network

Interactive Contrastive Learning For Self-Supervised Entity Alignment, Kaisheng Zeng, Zhenhao Dong, Lei Hou, Yixin Cao, Minghao Hu, Jifan Yu, Xin Lv, Lei Cao, Xin Wang, Haozhuang Liu, Yi Huang, Jing Wan, Juanzi Li Oct 2022

Interactive Contrastive Learning For Self-Supervised Entity Alignment, Kaisheng Zeng, Zhenhao Dong, Lei Hou, Yixin Cao, Minghao Hu, Jifan Yu, Xin Lv, Lei Cao, Xin Wang, Haozhuang Liu, Yi Huang, Jing Wan, Juanzi Li

Research Collection School Of Computing and Information Systems

Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without the use of pre-aligned entity pairs. The current state-of-the-art (SOTA) selfsupervised EA approach draws inspiration from contrastive learning, originally designed in computer vision based on instance discrimination and contrastive loss, and suffers from two shortcomings. Firstly, it puts unidirectional emphasis on pushing sampled negative entities far away rather than pulling positively aligned pairs close, as is done in the well-established supervised EA. Secondly, it advocates the minimum information requirement for self-supervised EA, while we argue that self-described KG’s side information (e.g., entity name, relation name, …

Go to article

Interactive Video Corpus Moment Retrieval Using Reinforcement Learning, Zhixin Ma, Chong-Wah Ngo Oct 2022

Interactive Video Corpus Moment Retrieval Using Reinforcement Learning, Zhixin Ma, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Known-item video search is effective with human-in-the-loop to interactively investigate the search result and refine the initial query. Nevertheless, when the first few pages of results are swamped with visually similar items, or the search target is hidden deep in the ranked list, finding the know-item target usually requires a long duration of browsing and result inspection. This paper tackles the problem by reinforcement learning, aiming to reach a search target within a few rounds of interaction by long-term learning from user feedbacks. Specifically, the system interactively plans for navigation path based on feedback and recommends a potential target that …

Go to article

Autoprtitle: A Tool For Automatic Pull Request Title Generation, Ivana Clairine Irsan, Ting Zhang, Ferdian Thung, David Lo, Lingxiao Jiang Oct 2022

Autoprtitle: A Tool For Automatic Pull Request Title Generation, Ivana Clairine Irsan, Ting Zhang, Ferdian Thung, David Lo, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

With the rise of the pull request mechanism in software development, the quality of pull requests has gained more attention. Prior works focus on improving the quality of pull request descriptions and several approaches have been proposed to automatically generate pull request descriptions. As an essential component of a pull request, pull request titles have not received a similar level of attention. To further facilitate automation in software development and to help developers draft high-quality pull request titles, we introduce AutoPRTitle. AutoPRTitle is specifically designed to generate pull request titles automatically. AutoPRTitle can generate a precise and succinct pull request …

Go to article

Taming Multi-Output Recommenders For Software Engineering, Christoph Treude Oct 2022

Taming Multi-Output Recommenders For Software Engineering, Christoph Treude

Research Collection School Of Computing and Information Systems

Recommender systems are a valuable tool for software engineers. For example, they can provide developers with a ranked list of files likely to contain a bug, or multiple auto-complete suggestions for a given method stub. However, the way these recommender systems interact with developers is often rudimentary—a long list of recommendations only ranked by the model’s confidence. In this vision paper, we lay out our research agenda for re-imagining how recommender systems for software engineering communicate their insights to developers. When issuing recommendations, our aim is to recommend diverse rather than redundant solutions and present them in ways that highlight …

Go to article

Artificial Intelligence, Consumers, And The Experience Economy, Hannah H. Chang, Anirban Mukherjee Oct 2022

Artificial Intelligence, Consumers, And The Experience Economy, Hannah H. Chang, Anirban Mukherjee

Research Collection Lee Kong Chian School Of Business

The term Artificial Intelligence (AI) was first used by McCarthy, Minsky, Rochester, and Shannon in a proposal for a summer research project in 1955 (Solomonoff, 1985). It is widely and commonly defined to be “the science and engineering of making intelligent machines” (McCarthy, 2006). Recent technological advances and methodological developments have made AI pervasive in new marketing offerings, ranging from self-driving cars, intelligent voice assistants such as Amazon’s Alexa, to burger-making robots at restaurants and rack-moving robots inside warehouses such as Amazon’s family of robots (Kiva, Pegasus, Xanthus) and delivery drones. There is optimism, and perhaps even over-optimism, of the …

Go to article

Using Machine Learning To Extract Insights From Consumer Data, Hannah H. Chang, Anirban Mukherjee Oct 2022

Using Machine Learning To Extract Insights From Consumer Data, Hannah H. Chang, Anirban Mukherjee

Research Collection Lee Kong Chian School Of Business

Advances in digital technology have led to the digitization of everyday activities of billions of people around the world, generating vast amounts of data on human behavior. From what people buy, to what information they search for, to how they navigate the social, digital, and physical world, human behavior can now be measured at a scale and level of precision that human history has not witnessed before. These developments have created unprecedented opportunities for those interested in understanding observable human behavior–social scientists, businesses, and policymakers—to (re)examine theoretical and substantive questions regarding people’s behavior. Moreover, technology has led to the emergence …

Go to article

Video Graph Transformer For Video Question Answering, Junbin Xiao, Pan Zhou, Tat-Seng Chua, Shuicheng Yan Oct 2022

Video Graph Transformer For Video Question Answering, Junbin Xiao, Pan Zhou, Tat-Seng Chua, Shuicheng Yan

Research Collection School Of Computing and Information Systems

This paper proposes a Video Graph Transformer (VGT) model for Video Quetion Answering (VideoQA). VGT’s uniqueness are two-fold: 1) it designs a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations, and dynamics for complex spatio-temporal reasoning; and 2) it exploits disentangled video and text Transformers for relevance comparison between the video and text to perform QA, instead of entangled crossmodal Transformer for answer classification. Vision-text communication is done by additional cross-modal interaction modules. With more reasonable video encoding and QA solution, we show that VGT can achieve much better performances on VideoQA tasks …

Go to article

Adaptive Structural Similarity Preserving For Unsupervised Cross Modal Hashing, Liang Li, Baihua Zheng, Weiwei Sun Oct 2022

Adaptive Structural Similarity Preserving For Unsupervised Cross Modal Hashing, Liang Li, Baihua Zheng, Weiwei Sun

Research Collection School Of Computing and Information Systems

Relation Extraction (RE) is a vital step to complete Knowledge Graph (KG) by extracting entity relations from texts. However, it usually suffers from the long-tail issue. The training data mainly concentrates on a few types of relations, leading to the lack of sufficient annotations for the remaining types of relations. In this paper, we propose a general approach to learn relation prototypes from unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient training data. We learn relation prototypes as an implicit factor between entities, which reflects the meanings of relations as well …

Go to article

Ngram-Oaxe: Phrase-Based Order-Agnostic Cross Entropy For Non-Autoregressive Machine Translation, Cunxiao Du, Zhaopeng Tu, Longyue Wang, Jing Jiang Oct 2022

Ngram-Oaxe: Phrase-Based Order-Agnostic Cross Entropy For Non-Autoregressive Machine Translation, Cunxiao Du, Zhaopeng Tu, Longyue Wang, Jing Jiang

Research Collection School Of Computing and Information Systems

Recently, a new training oaxe loss has proven effective to ameliorate the effect of multimodality for non-autoregressive translation (NAT), which removes the penalty of word order errors in the standard cross-entropy loss. Starting from the intuition that reordering generally occurs between phrases, we extend oaxe by only allowing reordering between ngram phrases and still requiring a strict match of word order within the phrases. Extensive experiments on NAT benchmarks across language pairs and data scales demonstrate the effectiveness and universality of our approach. Further analyses show that ngram noaxe indeed improves the translation of ngram phrases, and produces more fluent …

Go to article

Monarchical Constitutional Guardianship And Legal Metissage In Asia, De Maartje Visser, Andrew. Harding Oct 2022

Monarchical Constitutional Guardianship And Legal Metissage In Asia, De Maartje Visser, Andrew. Harding

Research Collection Yong Pung How School Of Law

This article presents a roadmap for examining the phenomenon of monarchy in Asia, which we conceive as a pluralist institution in a twofold manner. First, many monarchies discharge a wide range of roles and responsibilities ranging from the symbolic to the religious to the legal-political. These varied functions can be usefully captured under the notion of constitutional guardianship, and call for intersectional analysis. Second, it is common for monarchies to have metamorphosed from being purely endogenous institutions to becoming ones embedded in a scheme of limited, constitutional government under the influence of ideas from elsewhere. Monarchies should accordingly be viewed …

Go to article

Softskip: Empowering Multi-Modal Dynamic Pruning For Single-Stage Referring Comprehension, Dulanga Weerakoon, Vigneshwaran Subbaraju, Tuan Tran, Archan Misra Oct 2022

Softskip: Empowering Multi-Modal Dynamic Pruning For Single-Stage Referring Comprehension, Dulanga Weerakoon, Vigneshwaran Subbaraju, Tuan Tran, Archan Misra

Research Collection School Of Computing and Information Systems

Supporting real-time referring expression comprehension (REC) on pervasive devices is an important capability for human-AI collaborative tasks. Model pruning techniques, applied to DNN models, can enable real-time execution even on resource-constrained devices. However, existing pruning strategies are designed principally for uni-modal applications, and suffer a significant loss of accuracy when applied to REC tasks that require fusion of textual and visual inputs. We thus present a multi-modal pruning model, LGMDP, which uses language as a pivot to dynamically and judiciously select the relevant computational blocks that need to be executed. LGMDP also introduces a new SoftSkip mechanism, whereby 'skipped' visual …

Go to article

Accurate Generation Of Trigger-Action Programs With Domain-Adapted Sequence-To-Sequence Learning, Imam Nur Bani Yusuf, Lingxiao Jiang, David Lo Oct 2022

Accurate Generation Of Trigger-Action Programs With Domain-Adapted Sequence-To-Sequence Learning, Imam Nur Bani Yusuf, Lingxiao Jiang, David Lo

Research Collection School Of Computing and Information Systems

Trigger-action programming allows end users to write event-driven rules to automate smart devices and internet services. Users can create a trigger-action program (TAP) by specifying triggers and actions from a set of predefined functions along with suitable data fields for the functions. Many trigger-action programming platforms have emerged as the popularity grows, e.g., IFTTT, Microsoft Power Automate, and Samsung SmartThings. Despite their simplicity, composing trigger-action programs (TAPs) can still be challenging for end users due to the domain knowledge needed and enormous search space of many combinations of triggers and actions. We propose RecipeGen, a new deep learning-based approach that …

Go to article

Robustness And Cross-Lingual Transfer: An Exploration Of Out-Of-Distribution Scenario In Natural Language Processing, Yu, Sicheng Sep 2022

Robustness And Cross-Lingual Transfer: An Exploration Of Out-Of-Distribution Scenario In Natural Language Processing, Yu, Sicheng

Dissertations and Theses Collection (Open Access)

Most traditional machine learning or deep learning methods are based on the premise that training data and test data are independent and identical distributed, i.e., IID. However, it is just an ideal situation. In real-world applications, test set and training data often follow different distributions, which we refer to as the out of distribution, i.e., OOD, setting. As a result, models trained with traditional methods always suffer from an undesirable performance drop on the OOD test set. It's necessary to develop techniques to solve this problem for real applications. In this dissertation, we present four pieces of work in the …

Go to article

The Breadth Of Normative Standards: Antecedents And Consequences For Individuals And Organizations, Shilpa Madan, Shankha Basu, Sharon Ng, Krishna Savani Sep 2022

The Breadth Of Normative Standards: Antecedents And Consequences For Individuals And Organizations, Shilpa Madan, Shankha Basu, Sharon Ng, Krishna Savani

Research Collection Lee Kong Chian School Of Business

Normative standards refer to ideals to which people, products, and organizations are held. The present research (N = 2,224) investigates a novel construct—the breadth of normative standards, or the number of criteria that normative standards need to meet. Using archival and primary data in both organizational and consumer contexts, Studies 1–2 found that Indians’ and Singaporeans’ normative standards in several domains (e.g., a good job, a good body wash) needed to satisfy more criteria than those of Americans and the British. Using incentive-compatible designs, Studies 3–5 identified two downstream consequences of broader normative standards; decision-makers with broader standards pay greater …

Go to article

What You See Is What You Get? Measuring Companies' Projected Employer Image Attributes Via Companies' Employment Webpages, Christian P. Theurer, Philipp Schapers, Andranik Tumasjan, Isabell M. Welpe, Filip Lievens Sep 2022

What You See Is What You Get? Measuring Companies' Projected Employer Image Attributes Via Companies' Employment Webpages, Christian P. Theurer, Philipp Schapers, Andranik Tumasjan, Isabell M. Welpe, Filip Lievens

Research Collection Lee Kong Chian School Of Business

Information on a company's employment webpage sends signals about the employer image the company intends to project to applicants. Nonetheless, we know little about the content of recruitment signals sent via company employment webpages. This study develops a method to measure companies' projected employer image attributes based on their employment webpages. Specifically, we analyze companies' projected employer image attributes by applying computer-aided text analysis (CATA) to the employment webpages of 461 Fortune 500 companies (i.e., more than 11,100 individual pages). Our results show that projected employer image attributes remain relatively stable over time. Moreover, we find relatively low levels of …

Go to article

Hierarchical Semantic-Aware Neural Code Representation, Yuan Jiang, Xiaohong Su, Christoph Treude, Tiantian Wang Sep 2022

Hierarchical Semantic-Aware Neural Code Representation, Yuan Jiang, Xiaohong Su, Christoph Treude, Tiantian Wang

Research Collection School Of Computing and Information Systems

Code representation is a fundamental problem in many software engineering tasks. Despite the effort made by many researchers, it is still hard for existing methods to fully extract syntactic, structural and sequential features of source code, which form the hierarchical semantics of the program and are necessary to achieve a deeper code understanding. To alleviate this difficulty, we propose a new supervised approach based on the novel use of Tree-LSTM to incorporate the sequential and the global semantic features of programs explicitly into the representation model. Unlike previous techniques, our proposed model can not only learn low-level syntactic information within …

Go to article

Conclusion: Comparing Women's Representation In Asian Parliaments, Devin K. Joshi Aug 2022

Conclusion: Comparing Women's Representation In Asian Parliaments, Devin K. Joshi

Research Collection School of Social Sciences

This chapter explains important findings from this study while identifying common trends across Asia and the sub-regions of South Asia, Southeast Asia, and East Asia. It examines to what degree Asian parliamentarians have prioritized substantive representation of women (SRW). It assesses whether SRW was a primary reason or motivation behind why members of parliament (MPs) entered politics in the first place and whether they viewed SRW as a pressing issue for their governments to address. MPs interviewed in this study expressed what they felt were the most important issues today that need government’s attention. MPs were asked whether they make …

Go to article

Assertion, Stakes And Expected Blameworthiness: An Insensitive Invariantist Solution To The Bank Cases, Brandon Yip Aug 2022

Assertion, Stakes And Expected Blameworthiness: An Insensitive Invariantist Solution To The Bank Cases, Brandon Yip

Research Collection School of Social Sciences

Contextualists and Subject Sensitive Invariantists often cite the knowledge norm of assertion as part of their argument. They claim that the knowledge norms in conjunction with our intuitions about when a subject is properly asserting in low or high stakes contexts provides strong evidence that what counts as knowledge depends on practical factors. In this paper, I present new data to suggest they are mistaken in the way they think about cases involving high and low stakes and I show how insensitive invariantists can explain the data. I exploit recent work done on the distinction between flouting a norm and …

Go to article

Information Acquisition And Expected Returns: Evidence From Edgar Search Traffic, Frank Weikai Li, Chengzhu Sun Aug 2022

Information Acquisition And Expected Returns: Evidence From Edgar Search Traffic, Frank Weikai Li, Chengzhu Sun

Research Collection Lee Kong Chian School Of Business

This paper examines expected return information embedded in investors' information acquisition activity. Using a novel dataset containing investors' access of company filings through SEC's EDGAR system, we reverse engineer their expectations over future payoffs and show that the abnormal number of IPs searching for firms' financial statements strongly predict future returns. The return predictability stems from investors allocating more effort to firms with improving fundamentals and following exogeneous shock to underpricing. A long-short portfolio based on our measure of information acquisition activity generate monthly abnormal return of 80 basis points and does not reverse over the long-run.. In addition, the …

Go to article

Variational Graph Author Topic Modeling, Ce Zhang, Hady Wirawan Lauw Aug 2022

Variational Graph Author Topic Modeling, Ce Zhang, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

While Variational Graph Auto-Encoder (VGAE) has presented promising ability to learn representations for documents, most existing VGAE methods do not model a latent topic structure and therefore lack semantic interpretability. Exploring hidden topics within documents and discovering key words associated with each topic allow us to develop a semantic interpretation of the corpus. Moreover, documents are usually associated with authors. For example, news reports have journalists specializing in writing certain type of events, academic papers have authors with expertise in certain research topics, etc. Modeling authorship information could benefit topic modeling, since documents by the same authors tend to reveal …

Go to article

Realising Contingent Religious Subjects Through Relational Spaces Of Missionary Encounter, Orlando Woods Aug 2022

Realising Contingent Religious Subjects Through Relational Spaces Of Missionary Encounter, Orlando Woods

Research Collection School of Social Sciences

This paper explores the ways in which the religious subject can be a contingent position that is responsive to the broader socio-religious context within which it is expressed. These contingencies are acutely observed amongst short-term missionaries (STM), who seek out encounters with difference in pursuit of a more cosmopolitan subjectivity. Yet, whilst spaces of missionary encounter are inherently relational, the missions literature has tended to downplay the effects of relationality on the realisation of these subject positions. By focussing on the experiences of Singaporean missionaries working amongst Christian communities in Southeast Asia, I contribute a more nuanced and less predetermined …

Go to article

Holistic Combination Of Structural And Textual Code Information For Context Based Api Recommendation, Chi Chen, Xin Peng, Zhengchang Xing, Jun Sun, Xin Wang, Yifan Zhao, Wenyun Zhao Aug 2022

Holistic Combination Of Structural And Textual Code Information For Context Based Api Recommendation, Chi Chen, Xin Peng, Zhengchang Xing, Jun Sun, Xin Wang, Yifan Zhao, Wenyun Zhao

Research Collection School Of Computing and Information Systems

Context based API recommendation is an important way to help developers find the needed APIs effectively and efficiently. For effective API recommendation, we need not only a joint view of both structural and textual code information, but also a holistic view of correlated API usage in control and data flow graph as a whole. Unfortunately, existing API recommendation methods exploit structural or textual code information separately. In this work, we propose a novel API recommendation approach called APIRec-CST (API Recommendation by Combining Structural and Textual code information). APIRec-CST is a deep learning model that combines the API usage with the …

Go to article

Crosscbr: Cross‑View Contrastive Learning For Bundle Recommendation, Yunshan Ma, Yingzhi He, An Zhang, Xiang Wang, Tat-Seng Chua Aug 2022

Crosscbr: Cross‑View Contrastive Learning For Bundle Recommendation, Yunshan Ma, Yingzhi He, An Zhang, Xiang Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Bundle recommendation aims to recommend a bundle of related items to users, which can satisfy the users' various needs with one-stop convenience. Recent methods usually take advantage of both user-bundle and user-item interactions information to obtain informative representations for users and bundles, corresponding to bundle view and item view, respectively. However, they either use a unified view without differentiation or loosely combine the predictions of two separate views, while the crucial cooperative association between the two views' representations is overlooked.In this work, we propose to model the cooperative association between the two different views through cross-view contrastive learning. By encouraging …

Go to article

Learning To Ask Critical Questions For Assisting Product Search, Zixuan Li, Lizi Liao, Tat-Seng Chua Jul 2022

Learning To Ask Critical Questions For Assisting Product Search, Zixuan Li, Lizi Liao, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Product search plays an essential role in eCommerce. It was treated as a special type of information retrieval problem. Most existing works make use of historical data to improve the search performance, which do not take the opportunity to ask for user’s current interest directly. Some session-aware methods take the user’s clicks within the session as implicit feedback, but it is still just a guess on user’s preference. To address this problem, recent conversational or question-based search models interact with users directly for understanding the user’s interest explicitly. However, most users do not have a clear picture on what to …

Go to article

Q2r: A Query-To-Resolution System For Natural-Language Queries, Shiau Hong Lim, Laura Wynter Jul 2022

Q2r: A Query-To-Resolution System For Natural-Language Queries, Shiau Hong Lim, Laura Wynter

Research Collection School Of Computing and Information Systems

We present a system for document retrieval that combines direct classification with standard content-based retrieval approaches to significantly improve the relevance of the retrieved documents. Our system exploits the availability of an imperfect but sizable amount of labeled data from past queries. For domains such as technical support, the proposed approach enhances the system’s ability to retrieve documents that are otherwise ranked very low based on content alone. The system is easy to implement and can make use of existing text ranking methods, augmenting them through the novel Q2R orchestration framework. Q2R has been extensively tested and is in use …

Go to article

Harnessing Confidence For Report Aggregation In Crowdsourcing Environments, Hadeel Alhosaini, Xianzhi Wang, Lina Yao, Zhong Yang, Farookh Hussain, Ee-Peng Lim Jul 2022

Harnessing Confidence For Report Aggregation In Crowdsourcing Environments, Hadeel Alhosaini, Xianzhi Wang, Lina Yao, Zhong Yang, Farookh Hussain, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Crowdsourcing is an effective means of accomplishing human intelligence tasks by leveraging the collective wisdom of crowds. Given reports of various accuracy degrees from workers, it is important to make wise use of these reports to derive accurate task results. Intuitively, a task result derived from a sufficient number of reports bears lower uncertainty, and higher uncertainty otherwise. Existing report aggregation research, however, has largely neglected the above uncertainty issue. In this regard, we propose a novel report aggregation framework that defines and incorporates a new confidence measure to quantify the uncertainty associated with tasks and workers, thereby enhancing result …

Go to article

Dynamic Topic Models For Temporal Document Networks, Ce Zhang, Hady Wirawan Lauw Jul 2022

Dynamic Topic Models For Temporal Document Networks, Ce Zhang, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Dynamic topic models explore the time evolution of topics in temporally accumulative corpora. While existing topic models focus on the dynamics of individual documents, we propose two neural topic models aimed at learning unified topic distributions that incorporate both document dynamics and network structure. For the first model, by adding a time dimension, we propose Time-Aware Optimal Transport, which measures the probability of a link between two differently timestamped documents using their semantic distance. Since the gradually evolving topological structure of network may also influence the establishment of a new link, for the second model, we further design a Temporal …

Go to article

Order Constraints In Optimal Transport, Fabian Lim, Laura Wynter, Shiau Hong Lim Jul 2022

Order Constraints In Optimal Transport, Fabian Lim, Laura Wynter, Shiau Hong Lim

Research Collection School Of Computing and Information Systems

Optimal transport is a framework for comparing measures whereby a cost is incurred for transporting one measure to another. Recent works have aimed to improve optimal transport plans through the introduction of various forms of structure. We introduce novel order constraints into the optimal transport formulation to allow for the incorporation of structure. We define an efficient method for obtaining explainable solutions to the new formulation that scales far better than standard approaches. The theoretical properties of the method are provided. We demonstrate experimentally that order constraints improve explainability using the e-SNLI (Stanford Natural Language Inference) dataset that includes human-annotated …

Go to article

Communication In The Gig Economy: Buying And Selling In Online Freelance Marketplaces, Stephan Ludwig, Dennis Herhausen, Dhruv Grewal, Liliana Bove, Sabine Benoit, Ko De Ruyter, Peter Urwin Jul 2022

Communication In The Gig Economy: Buying And Selling In Online Freelance Marketplaces, Stephan Ludwig, Dennis Herhausen, Dhruv Grewal, Liliana Bove, Sabine Benoit, Ko De Ruyter, Peter Urwin

Research Collection Lee Kong Chian School Of Business

The proliferating gig economy relies on online freelance marketplaces, which support relatively anonymous interactions through text-based messages. Informational asymmetries thus arise that can lead to exchange uncertainties between buyers and freelancers. Conventional marketing thought recommends reducing such uncertainty. However, uncertainty reduction and uncertainty management theories indicate that buyers and freelancers might benefit more from balancing-rather than reducing-uncertainty, such as by strategically adhering to or deviating from common communication principles. With dyadic analyses of calls for bids and bids from a leading online freelance marketplace, this study reveals that buyers attract more bids from freelancers when they provide moderate degrees of …

Go to article

Declaration-Based Prompt Tuning For Visual Question Answering, Yuhang Liu, Wei Wei, Feida Zhu, Feida Zhu Jul 2022

Declaration-Based Prompt Tuning For Visual Question Answering, Yuhang Liu, Wei Wei, Feida Zhu, Feida Zhu

Research Collection School Of Computing and Information Systems

In recent years, the pre-training-then-fine-tuning paradigm has yielded immense success on a wide spectrum of cross-modal tasks, such as visual question answering (VQA), in which a visual-language (VL) model is first optimized via self-supervised task objectives, e.g., masked language modeling (MLM) and image-text matching (ITM), and then fine-tuned to adapt to downstream task (e.g., VQA) via a brand-new objective function, e.g., answer prediction. However, the inconsistency of the objective forms not only severely limits the generalization of pre-trained VL models to downstream tasks, but also requires a large amount of labeled data for fine-tuning. To alleviate the problem, we propose …

Go to article

First Prev Next Last