Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (1116)
- Computer Sciences (1107)
- Databases and Information Systems (529)
- Social and Behavioral Sciences (485)
- Artificial Intelligence and Robotics (356)
-
- Business (207)
- Software Engineering (190)
- International and Area Studies (184)
- Asian Studies (180)
- Graphics and Human Computer Interfaces (154)
- Numerical Analysis and Scientific Computing (149)
- Communication (130)
- Arts and Humanities (120)
- Programming Languages and Compilers (112)
- Law (101)
- Social Media (96)
- Psychology (81)
- Sociology (71)
- Education (68)
- Political Science (66)
- Engineering (63)
- Organizational Behavior and Theory (57)
- Philosophy (49)
- Computer Engineering (45)
- Public Affairs, Public Policy and Public Administration (35)
- Strategic Management Policy (33)
- Information Security (32)
- Economics (31)
- Higher Education (30)
- Theory and Algorithms (30)
- Keyword
-
- Social media (45)
- Singapore (38)
- Natural language processing (32)
- Deep learning (28)
- Machine learning (24)
-
- China (22)
- Large Language Models (20)
- Large language models (20)
- Culture (18)
- LLMs (18)
- Sentiment analysis (17)
- Text mining (16)
- Twitter (16)
- Software engineering (14)
- Generative AI (13)
- Indonesia (13)
- Language (13)
- Artificial intelligence (12)
- Neural networks (12)
- Computational linguistics (11)
- Creativity (10)
- Data mining (10)
- Large Language Model (10)
- Natural Language Processing (10)
- Performance (10)
- Bilingualism (9)
- Language model (9)
- Artificial Intelligence (8)
- Christianity (8)
- Deep Learning (8)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (1049)
- Research Collection School of Social Sciences (236)
- Research Collection Lee Kong Chian School Of Business (131)
- Research Collection Yong Pung How School Of Law (94)
- Dissertations and Theses Collection (Open Access) (58)
-
- Research Collection College of Integrative Studies (34)
- Research Collection School Of Accountancy (21)
- Research Collection School Of Economics (19)
- Asian Management Insights (6)
- Institute of Societal Leadership Research Collection (4)
- Perspectives@SMU (3)
- Research Collection Library (3)
- SCIS Student Publications (3)
- Student Publications (3)
- Centre for Computational Law (2022-2025) (2)
- Digital Narratives of Asia (2)
- FORCE 2026 (2)
- Knowledge@SMU (2)
- Social Space (2)
- 2008 Asian Business & Rule of Law initiative (1)
- 2012 AAPBS Academic Conference: Asian Business Leaders with a Global Mindset (1)
- 2012 Emerging Trends in Research Assessment Seminar (1)
- 2024 AI for Research Week (1)
- CCX Research (1)
- Dissertations and Theses Collection (1)
- Library Events (1)
- Lien Centre for Social Innovation: Research (1)
- Oral History Collection (1)
- PhD Student’s Publications Collection (1)
- Report to Stakeholders (1)
- Publication Type
- File Type
Articles 1261 - 1290 of 1692
Full-Text Articles in Entire DC Network
Nirmal: Automatic Identification Of Software Relevant Tweets Leveraging Language Model, Abishek Sharma, Yuan Tian, David Lo
Nirmal: Automatic Identification Of Software Relevant Tweets Leveraging Language Model, Abishek Sharma, Yuan Tian, David Lo
Research Collection School Of Computing and Information Systems
Twitter is one of the most widely used social media platforms today. It enables users to share and view short 140-character messages called 'tweets'. About 284 million active users generate close to 500 million tweets per day. Such rapid generation of user generated content in large magnitudes results in the problem of information overload. Users who are interested in information related to a particular domain have limited means to filter out irrelevant tweets and tend to get lost in the huge amount of data they encounter. A recent study by Singer et al. found that software developers use Twitter to …
Is The Ability To Speak Multiple Languages Always A Good Thing?, Singapore Management University
Is The Ability To Speak Multiple Languages Always A Good Thing?, Singapore Management University
Perspectives@SMU
People who speak more than one language are more likely to be smarter, but they might have a smaller vocabulary
Use Of A High-Value Social Audience Index For Target Audience Identification On Twitter, Siaw Ling Lo, David Cornforth, Raymond. Chiong
Use Of A High-Value Social Audience Index For Target Audience Identification On Twitter, Siaw Ling Lo, David Cornforth, Raymond. Chiong
Research Collection School Of Computing and Information Systems
With the large and growing user base of social media, it is not an easy feat to identify potential customers for business. This is mainly due to the challenge of extracting commercially viable contents from the vast amount of free-form conversations. In this paper, we analyse the Twitter content of an account owner and its list of followers through various text mining methods and segment the list of followers via an index. We have termed this index as the High-Value Social Audience (HVSA) index. This HVSA index enables a company or organisation to devise their marketing and engagement plan according …
Bridging The Vocabulary Gap Between Health Seekers And Healthcare Knowledge, Liqiang Nie, Yiliang Zhao, Akbari Mohammad, Jialie Shen, Tat-Seng Chua
Bridging The Vocabulary Gap Between Health Seekers And Healthcare Knowledge, Liqiang Nie, Yiliang Zhao, Akbari Mohammad, Jialie Shen, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
The vocabulary gap between health seekers and providers has hindered the cross-system operability and the interuser reusability. To bridge this gap, this paper presents a novel scheme to code the medical records by jointly utilizing local mining and global learning approaches, which are tightly linked and mutually reinforced. Local mining attempts to code the individual medical record by independently extracting the medical concepts from the medical record itself and then mapping them to authenticated terminologies. A corpus-aware terminology vocabulary is naturally constructed as a byproduct, which is used as the terminology space for global learning. Local mining approach, however, may …
Dominic Puthucheary [Malaysia, Member Of Parliament, Founder Barisan Sosialis], Dominic Puthucheary
Dominic Puthucheary [Malaysia, Member Of Parliament, Founder Barisan Sosialis], Dominic Puthucheary
Digital Narratives of Asia
Founder Vice-President, Barisan Sosialis, and former Malaysian Member of Parliament for Nibong Tebal, Dominic Puthucheary, recalls how he was inducted into politics, then trade union movement during the anti-colonial era. He presented his retrospective views on Mr Lee Kuan Yew, and the failure of the Left movement in the Cold War realities.
Mining User Viewpoints In Online Discussions, Minghui Qiu
Mining User Viewpoints In Online Discussions, Minghui Qiu
Dissertations and Theses Collection (Open Access)
Online discussion forums are a type of social media which contains rich usercontributed facts, opinions, and user interactions on diverse topics. The large volume of opinionated data generated in online discussions provides an ideal testbed for user opinion mining. In particular, mining user opinions on social and political issues from online discussions is useful not only to government organizations and companies but also to social and political scientists. In this dissertation, we propose to study the task of mining user viewpoints or stances from online discussions on social and political issues. Specifically, we will talk about our proposed approaches for …
Toward Mobile Robots Reasoning Like Humans, Jean Oh, Arne Suppe, Felix Duvallet, Abdeslam Boularias, Luis Navarro-Serment, Martial Hebert, Anthony Stentz, Jerry Vinokurov, Oscar Romero, Christian Lebiere, Robert Dean
Toward Mobile Robots Reasoning Like Humans, Jean Oh, Arne Suppe, Felix Duvallet, Abdeslam Boularias, Luis Navarro-Serment, Martial Hebert, Anthony Stentz, Jerry Vinokurov, Oscar Romero, Christian Lebiere, Robert Dean
Research Collection School Of Computing and Information Systems
Robots are increasingly becoming key players in human-robot teams. To become effective teammates, robots must possess profound understanding of an environment, be able to reason about the desired commands and goals within a specific context, and be able to communicate with human teammates in a clear and natural way. To address these challenges, we have developed an intelligence architecture that combines cognitive components to carry out high-level cognitive tasks, semantic perception to label regions in the world, and a natural language component to reason about the command and its relationship to the objects in the world. This paper describes recent …
Integrated Intelligence For Human-Robot Teams, Jean Oh, Et. Al.
Integrated Intelligence For Human-Robot Teams, Jean Oh, Et. Al.
Research Collection School Of Computing and Information Systems
With recent advances in robotics technologies and autonomous systems, the idea of human-robot teams is gaining ever-increasing attention. In this context, our research focuses on developing an intelligent robot that can autonomously perform non-trivial, but specific tasks conveyed through natural language. Toward this goal, a consortium of researchers develop and integrate various types of intelligence into mobile robot platforms, including cognitive abilities to reason about high-level missions, perception to classify regions and detect relevant objects in an environment, and linguistic abilities to associate instructions with the robot’s world model and to communicate with human teammates in a natural way. This …
Short Selling Pressure, Stock Price Behavior, And Management Forecast Precision: Evidence From A Natural Experiment, Yinghua Li, Liandong Zhang
Short Selling Pressure, Stock Price Behavior, And Management Forecast Precision: Evidence From A Natural Experiment, Yinghua Li, Liandong Zhang
Research Collection School Of Accountancy
Using a natural experiment (Regulation SHO), we show that short selling pressure and consequent stock price behavior have a causal effect on managers' voluntary disclosure choices. Specifically, we find that managers respond to a positive exogenous shock to short selling pressure and price sensitivity to bad news by reducing the precision of bad news forecasts. This finding on management forecasts appears to be generalizable to other corporate disclosures. In particular, we find that, in response to increased short selling pressure, managers also reduce the readability (or increase the fuzziness) of bad news annual reports. Overall, our results suggest that maintaining …
Within & Without: Singapore In The World; The World In Singapore, Eng Fong Pang, Arnoud De Meyer
Within & Without: Singapore In The World; The World In Singapore, Eng Fong Pang, Arnoud De Meyer
Research Collection Lee Kong Chian School Of Business
Contents: We, the Citizens of Singapore by Priscilla Chia, Trenton James Riggs; Birth of a Nation: Ways of Celebrating by Celine Alexandra Fogde, Diana Khanh Nguyen, Paul Antoine Victor, Shu Chong Chen, Teo Yi Heng; Building Cross-cultural Bridges by Vani Shriya, Timoteo Marra, Svenja Nicole Schulte, Seow Guan Wen, Niklas Miro Utrobicic; Faces and Facets of Singapore by Felix Brockerhoff, Elizabeth Fong Lin, Kevin Ng Boon Kiat, Racheal Wong Shu Yi, Tam Zhi Yang; Missing the Forest for the (Super) Trees by Nick Chiam Zhi Wen, Teo Yi Heng; Singapore: The Country Where You Cannot Chew Gum? by Felix Brockerhoff; …
Disciplines, Area Studies, And Publics: Rethinking Sociology In A Global World, Hiro Saito
Disciplines, Area Studies, And Publics: Rethinking Sociology In A Global World, Hiro Saito
Research Collection School of Social Sciences
Why did Contemporary Sociology, an official journal of the American Sociological Association, ask me to review these two books on Japan edited and written by anthropologists? This question sounds trivial and even irrelevant at first. However, when the question’s three overlapping registers— why Japan, why anthropology, and why me (a Japanese sociologist trained in the United States)—are recognized, they should prompt readers of Contemporary Sociology to reexamine the relationship between disciplines and area studies, on the one hand, and the relationship between sociologists and publics, on the other. In fact, I suggest that this reexamination be an urgent task in …
Effects Of Training Datasets On Both The Extreme Learning Machine And Support Vector Machine For Target Audience Identification On Twitter, Siaw Ling Lo, David Cornforth, Raymond Chiong
Effects Of Training Datasets On Both The Extreme Learning Machine And Support Vector Machine For Target Audience Identification On Twitter, Siaw Ling Lo, David Cornforth, Raymond Chiong
Research Collection School Of Computing and Information Systems
The ability to identify or predict a target audience from the increasingly crowded social space will provide a company some competitive advantage over other companies. In this paper, we analyze various training datasets, which include Twitter contents of an account owner and its list of followers, using features generated in different ways for two machine learning approaches - the Extreme Learning Machine (ELM) and Support Vector Machine (SVM). Various configurations of the ELM and SVM have been evaluated. The results indicate that training datasets using features generated from the owner tweets achieve the best performance, relative to other feature sets. …
The Dili Report: National Landscape, Current Challenges And Opportunities For Growth, Institute For Societal Leadership, Lai Cheng Lim
The Dili Report: National Landscape, Current Challenges And Opportunities For Growth, Institute For Societal Leadership, Lai Cheng Lim
Institute of Societal Leadership Research Collection
Timor-Leste, Asia’s newest nation, is located in Southeast Asia, on the southernmost edge of the Indonesian archipelago. The country was colonised by the Portuguese for over 450 years, occupied by the Indonesians for 24 years and administered by the United Nations for two and a half years. As a nation, Timor-Leste has had a very traumatic birth.
Issues Of Social Data Analytics With A New Method For Sentiment Analysis Of Social Media Data, Zhaoxia Wang, Victor J. C. Tong, David Chan
Issues Of Social Data Analytics With A New Method For Sentiment Analysis Of Social Media Data, Zhaoxia Wang, Victor J. C. Tong, David Chan
Research Collection School of Social Sciences
Social media data consists of feedback, critiques and other comments that are posted online by internet users. Collectively, these comments may reflect sentiments that are sometimes not captured in traditional data collection methods such as administering a survey questionnaire. Thus, social media data offers a rich source of information, which can be adequately analyzed and understood. In this paper, we survey the extant research literature on sentiment analysis and discuss various limitations of the existing analytical methods. A major limitation in the large majority of existing research is the exclusive focus on social media data in the English language. There …
Rethinking Governance In Management Research: From The Editors, Laszlo Tihanyi, Scott Graffin, Gerard George
Rethinking Governance In Management Research: From The Editors, Laszlo Tihanyi, Scott Graffin, Gerard George
Research Collection Lee Kong Chian School Of Business
In the field of management, the study of governance has primarily dealt with decision-making by boards of directors, chief executives, and senior managers. The corporate governance literature has generated important insights regarding incentive alignment, risk taking, and coordination challenges. Emerging trends, highlighted in this issue, raise new questions regarding managerial roles, organizational contexts, internal and social processes, and changes in governance over time. We encourage management scholars to rethink their approach to governance research by considering stakeholder engagement, the implications of big data, social impact, global dimensions, and comparative analysis of governance. A broadened conceptualization of governance may also deal …
How Firms Respond To Financial Restatement: Ceo Successors And External Reactions, David Gomulya, Warren Boeker
How Firms Respond To Financial Restatement: Ceo Successors And External Reactions, David Gomulya, Warren Boeker
Research Collection Lee Kong Chian School Of Business
Although past studies have paid considerable attention to firms' reputations, few have investigated the actions that firms take following a reputation-damaging event. We identify firms involved in financial earnings restatements and examine whether naming a successor CEO with specific qualities serves to signal the seriousness of a firm's efforts to restore its reputation. Using theories of market signaling, we argue that attributes of successor CEOs significantly influence the reactions of key external constituencies. In particular, firms with more severe restatement tend to name successors who have prior CEO or turnaround experience and a more elite education. The naming of such …
Rural Electrification And Development In South Korea, Terry Van Gevelt
Rural Electrification And Development In South Korea, Terry Van Gevelt
Research Collection College of Integrative Studies
In fifteen years, South Korea went from providing only 12% of rural households with electricity to providing 98% of rural households with electricity for lighting and productive uses. This paper provides an analysis of rural electrification and development in South Korea from 1965 to 1979 and finds that rural electrification contributed to a significant increase in rural household income levels and improved the quality of life in villages substantially. At the same time, rural electrification did not benefit the poorest quartile of rural households, increased economic and social inequality, led to a significant increase in household debt, and accelerated migration …
Introduction To Issue On Education For A Tolerant And Multicultural Indonesia, Lyn Parker, Chang Yau Hoon
Introduction To Issue On Education For A Tolerant And Multicultural Indonesia, Lyn Parker, Chang Yau Hoon
Research Collection School of Social Sciences
Ethnic, religious and linguistic diversity is intrinsic to the concept of Indonesia. The national motto of Bhinneka Tunggal Ika, often translated as ‘Unity in Diversity’, though more directly translatable as ‘Diverse but One’, is emblazoned on the national symbol, the Garuda, which appears in classrooms, offices, statues and even living rooms all around the country. Indonesia has long enjoyed the reputation of a diverse and tolerant country. However, after the fall of Suharto in May 1998, it seemed to erupt in a conflagration of violence. Religious and ethnic conflicts alerted both citizens and scholars of Indonesia to the danger of …
Extracting Interest Tags From Twitter User Biographies, Ying Ding, Jing Jiang
Extracting Interest Tags From Twitter User Biographies, Ying Ding, Jing Jiang
Research Collection School Of Computing and Information Systems
Twitter, one of the most popular social media platforms, has been studied from different angles. One of the important sources of information in Twitter is users’ biographies, which are short self-introductions written by users in free form. Biographies often describe users’ background and interests. However, to the best of our knowledge, there has not been much work trying to extract information from Twitter biographies. In this work, we study how to extract information revealing users’ personal interests from Twitter biographies. A sequential labeling model is trained with automatically constructed labeled data. The popular patterns expressing user interests are extracted and …
Anomaly Detection Through Enhanced Sentiment Analysis On Social Media Data, Zhaoxia Wang, Victor Joo, Chuan Tong, Xin Xin, Hoong Chor Chin
Anomaly Detection Through Enhanced Sentiment Analysis On Social Media Data, Zhaoxia Wang, Victor Joo, Chuan Tong, Xin Xin, Hoong Chor Chin
Research Collection School Of Computing and Information Systems
Anomaly detection in sentiment analysis refers to detecting abnormal opinions, sentiment patterns or special temporal aspects of such patterns in a collection of data. The anomalies detected may be due to sudden sentiment changes hidden in large amounts of text. If these anomalies are undetected or poorly managed, the consequences may be severe, e.g. A business whose customers reveal negative sentiments and will no longer support the establishment. Social media platforms, such as Twitter, provide a vast source of information, which includes user feedback, opinion and information on most issues. Many organizations also leverage social media platforms to publish information …
Identifying The High-Value Social Audience From Twitter Through Text-Mining Methods, Siaw Ling Lo, David Cornforth, Raymond Chiong
Identifying The High-Value Social Audience From Twitter Through Text-Mining Methods, Siaw Ling Lo, David Cornforth, Raymond Chiong
Research Collection School Of Computing and Information Systems
Doing business on social media has become a common practice for many companies these days. While the contents shared on Twitter and Facebook offer plenty of opportunities to uncover business insights, it remains a challenge to sift through the huge amount of social media data and identify the potential social audience who is highly likely to be interested in a particular company. In this paper, we analyze the Twitter content of an account owner and its list of followers through various text mining methods, which include fuzzy keyword matching, statistical topic modeling and machine learning approaches. We use tweets of …
Vireo-Tno @ Trecvid 2014: Multimedia Event Detection And Recounting (Med And Mer), Chong-Wah Ngo, Yi-Jie Lu, Hao Zhang, Ting Yao, Chun-Chet Tan, Lei Pang, Maaike De Boer, John Schavemaker, Klamer Schutte, Wessel Kraaij
Vireo-Tno @ Trecvid 2014: Multimedia Event Detection And Recounting (Med And Mer), Chong-Wah Ngo, Yi-Jie Lu, Hao Zhang, Ting Yao, Chun-Chet Tan, Lei Pang, Maaike De Boer, John Schavemaker, Klamer Schutte, Wessel Kraaij
Research Collection School Of Computing and Information Systems
This paper presents an overview and comparative analysis of our systems designed for TRECVID 2014 [1] multimedia event detection (MED) and recounting (MER) tasks, including all sub-tasks for Pre-Specified (PS) event detection, all sub-tasks except 100Ex for Ad-Hoc (AH) event detection, and 010Ex sub-task for both PS and AH event recounting. Multimedia Event Detection (MED) : Our main focus for the MED task is on the study of a new zero-example system, which aims to solve the 000Ex and SQ problems. The system can run either fully automatically or semi-automatically. Specifically, we test the automatic run in 000Ex submission and …
Trade And Divergence In Education Systems, Fali Huang, Pao-Li Chang
Trade And Divergence In Education Systems, Fali Huang, Pao-Li Chang
Research Collection School Of Economics
This article presents a theory on the endogenous choice of education policy and the two-way causal relationship between trade and education systems. A country’s education system determines its talent distribution and comparative advantage; the possibility of trade by raising the returns to the sector of comparative advantage in turn induces countries to further differentiate their education systems and reinforces the initial pattern of comparative advantage. Specifically, the Nash equilibrium choice of education systems by two countries interacting strategically are necessarily more divergent than their autarky choices, and yet less than what is socially optimal for the world.
Mutual Funds And Information Diffusion: The Role Of Country-Level Governance, Chunmei Lin, Massimo Massa, Hong Zhang
Mutual Funds And Information Diffusion: The Role Of Country-Level Governance, Chunmei Lin, Massimo Massa, Hong Zhang
Research Collection Lee Kong Chian School Of Business
We hypothesize that poor country-level governance, which makes public information less reliable, induces fund managers to increase their use of semipublic information. Utilizing data from international mutual funds and stocks over the 2000-2009 period, we find that semipublic information-related stock rebalancing can be five times higher in countries with the worst quality of governance than in countries with the best. The use of semipublic information increases price informativeness but also increases information asymmetry and reduces stock liquidity. It also intensified the price impact and liquidity crunch during the recent global financial crisis.
Deep Learning For Content-Based Image Retrieval: A Comprehensive Study, Ji Wan, Dayong Wang, Steven C. H. Hoi, Pengcheng Wu, Jianke Zhu, Yongdong Zhang, Jintao Li
Deep Learning For Content-Based Image Retrieval: A Comprehensive Study, Ji Wan, Dayong Wang, Steven C. H. Hoi, Pengcheng Wu, Jianke Zhu, Yongdong Zhang, Jintao Li
Research Collection School Of Computing and Information Systems
Learning effective feature representations and similarity measures are crucial to the retrieval performance of a content-based image retrieval (CBIR) system. Despite extensive research efforts for decades, it remains one of the most challenging open problems that considerably hinders the successes of real-world CBIR systems. The key challenge has been attributed to the well-known "semantic gap" issue that exists between low-level image pixels captured by machines and high-level semantic concepts perceived by human. Among various techniques, machine learning has been actively investigated as a possible direction to bridge the semantic gap in the long term. Inspired by recent successes of deep …
Derrida And Comparative Philosophy, Steven Burik
Derrida And Comparative Philosophy, Steven Burik
Research Collection School of Social Sciences
This article argues that Derrida’s thinking is relevant to comparative philosophy. To illustrate this, at various stages classical Daoism is compared with Derrida’s thought, to highlight Derrida’s “applicability” and to see how using Derrida can contribute to new interpretations of Daoism. The article first looks into Derrida’s engagement (or lack thereof) with non-Western thought, and then proceeds to his extensive work regarding language and translation, comparing this with views on classical Chinese language and translation of key Daoist characters. It then explores Derrida’s efforts at opening up philosophy to its outside, and argues that he was very much concerned with …
On Joint Modeling Of Topical Communities And Personal Interest In Microblogs, Tuan-Anh Hoang, Ee Peng Lim
On Joint Modeling Of Topical Communities And Personal Interest In Microblogs, Tuan-Anh Hoang, Ee Peng Lim
Research Collection School Of Computing and Information Systems
In this paper, we propose the Topical Communities and Personal Interest (TCPI) model for simultaneously modeling topics, topical communities, and users’ topical interests in microblogging data. TCPI considers different topical communities while differentiating users’ personal topical interests from those of topical communities, and learning the dependence of each user on the affiliated communities to generate content. This makes TCPI different from existing models that either do not consider the existence of multiple topical communities, or do not differentiate between personal and community’s topical interests. Our experiments on two Twitter datasets show that TCPI can effectively mine the representative topics for …
Linguistic Analysis Of Toxic Behavior In An Online Video Game, Haewoon Kwak, Telefonica
Linguistic Analysis Of Toxic Behavior In An Online Video Game, Haewoon Kwak, Telefonica
Research Collection School Of Computing and Information Systems
In this paper we explore the linguistic components of toxic behavior by using crowdsourced data from over 590 thousand cases of accused toxic players in a popular match-based competition game, League of Legends. We perform a series of linguistic analyses to gain a deeper understanding of the role communication plays in the expression of toxic behavior. We characterize linguistic behavior of toxic players and compare it with that of typical players in an online competition game. We also find empirical support describing how a player transitions from typical to toxic behavior. Our findings can be helpful to automatically detect and …
Imagespirit: Verbal Guided Image Parsing, Ming-Ming Cheng, Shuai Zheng, Wen-Yan Lin, Vibhav Vineet, Paul Sturgess, Nigel Crook, Niloy J. Mitra, Philip Torr
Imagespirit: Verbal Guided Image Parsing, Ming-Ming Cheng, Shuai Zheng, Wen-Yan Lin, Vibhav Vineet, Paul Sturgess, Nigel Crook, Niloy J. Mitra, Philip Torr
Research Collection School Of Computing and Information Systems
Humans describe images in terms of nouns and adjectives while algorithms operate on images represented as sets of pixels. Bridging this gap between how humans would like to access images versus their typical representation is the goal of image parsing, which involves assigning object and attribute labels to pixels. In this article we propose treating nouns as object labels and adjectives as visual attribute labels. This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images. We propose an efficient (interactive time) solution. Using the extracted …
Entity Linking On Microblogs With Spatial And Temporal Signals, Yuan Fang, Ming-Wei Chang
Entity Linking On Microblogs With Spatial And Temporal Signals, Yuan Fang, Ming-Wei Chang
Research Collection School Of Computing and Information Systems
Microblogs present an excellent opportunity for monitoring and analyzing world happenings. Given that words are often ambiguous, entity linking becomes a crucial step towards understanding microblogs. In this paper, we re-examine the problem of entity linking on microblogs. We first observe that spatiotemporal (i.e., spatial and temporal) signals play a key role, but they are not utilized in existing approaches. Thus, we propose a novel entity linking framework that incorporates spatiotemporal signals through a weakly supervised process. Using entity annotations1 on real-world data, our experiments show that the spatiotemporal model improves F1 by more than 10 points over existing systems. …