• With the growth in volume and variety of UGC on the web, the way that people seek and consume information and knowledge is changing. Given the sheer volume of UGCs in any given topic, it becomes harder and extremely time-consuming for users to grasp and follow the evolution of knowledge even in their domains of interests. To better enhance the aggregation, communication, and corroboration of insights and knowledge of the crowd, this research explores techniques to automatically analyse, organize, and summarize large amount of UGCs on a specific topic so as to encourage macro-level and micro-level information access and knowledge creation.
    Read More
  • Social media portals like Twitter, Facebook, Google+, and various forum sites contain the everyday thoughts, opinions, and experiences of their online users. Parts of these UGCs reflect and reveal information about organizations such as the companies, banks, government organizations, and universities etc. These UGC about organizations provide important and timely indicators on the spontaneous and often genuine views of the users, fans and customers of the organizations. It is thus invaluable for organizations to keep track of such views to get live feedbacks from their users and perform live analytics on such data to discover both market insights and foresights and provide better services to their users.
    Read More
  • The proliferation of user-generated contents in the form of text, images, and videos has led to a surge of research into "user-centric" multimedia applications, such as multimedia search, recommendation, and advertisement etc. Pivotal to these research and development efforts is the understanding of users' intents in large-scale media search. In particular, we have been working to narrow down the "Intention Gap" in multimedia search. As illustrated in the picture, there often exists an "Intention Gap" between a user's search intent and the query, posing difficulty in understanding user's search intent by the search engine and leading to unsatisfactory search results.
    Read More
  • The widespread use of smart phone has led to the proliferation of location based social networks (LBSNs), such as the Twitter, Foursquare, Instagram and YouTube. These networks enable people from all walks of life to exchange their thoughts, disseminate multimedia information, share travelling experience and connect to each other more conveniently than ever before. These developments also spur the need for many location based services, such as POI recommendation etc., in order to better help users in their daily lives.
    Read More
  • We seek to improve the interpretation of temporal relationships between interesting units of text, including events and time expressions. Our approach leverages on the inherent structure of English, making use of deeper semantic analysis instead of just surface lexical features. We find that this approach allows us to out-perform other state-of-the-art systems.
    Read More
  • Mobile applications (apps) are soaring in popularity and creating economic opportunities for app developers, companies, and marketers. The selection available in App Stores is growing rapidly as new apps are approved and released daily. While this growth has provided users with a myriad of apps, the sheer number of choices also makes it more difficult for users to find apps that are relevant to their interests. Recommender systems that depend on previous user ratings (i.e., collaborative filtering, or CF) can address this problem for apps that have sufficient past ratings. But for apps that are newly released, CF does not have any user ratings to base recommendations on, causing the cold-start problem. We explore various ways to provide app-recommendations under cold-start scenarios.
    Read More
  • The Summarizer from the Web IR / NLP Group (WING), hence SWING, is a modular, state-of-the-art automatic extractive text summarization system. It produces informative summaries from multiple topic related documents using a supervised learning model. SWING is also the best performing summarizer at the international TAC 2011 competition, getting high marks on the ROUGE evaluation measure. The summarizer is optimized for news articles, and is freely available for download.
    Read More
  • By: Rubaiat Habib Kazi, Fanny Chevalier, Tovi Grossman, Shengdong Zhao, George Fitzmaurice Draco, a sketch-based interface that allows artists and casual users alike to add a rich set of animation effects to their drawings, seemingly bringing illustrations to life. While previous systems have introduced sketch-based animations for individual objects, our contribution is a unified framework of motion controls that allows users to seamlessly add coordinated motions to object collections. We propose a framework built around kinetic textures, which provide continuous animation effects while preserving the unique timeless nature of still illustrations. This enables many dynamic effects difficult or not possible with previous sketch-based tools, such as a school of fish swimming, tree leaves blowing in the wind, or water rippling in a pond. We describe our implementation and illustrate the repertoire of animation effects it supports. A user study with professional animators and casual users demonstrates the variety of animations, applications and creative possibilities our tool provides.
    Read More
  • By: Debyjoti Ghosh, Pin Sym Foong, Shengdong Zhao, Di Chen, Morten Fjeld “Interact with CUI’s and edit responses in eyes- and hands-busy modes.” We present EDITalk, a novel voice-based, eyes-free word processing interface. We used a Wizard-of-Oz elicitation study to investigate the viability of eyes-free word processing in the mobile context and to elicit user requirements for such scenarios. Results showed that meta-level operations like highlight and comment, and core operations like insert, delete and replace are desired by users. However, users were challenged by the lack of visual feedback and the cognitive load of remembering text while editing it. We then studied a commercial-grade dictation application and discovered serious limitations that preclude comfortable speak-to-edit interactions. We address these limitations through EDITalk's closed-loop interaction design, enabling eyes-free operation of both meta-level and core word processing operations in the mobile context. Finally, we discuss implications for the design of future mobile, voice-based, eyes-free word processing interface.
    Read More