My main research instrest is monolingual translation. I proposed the MonoTrans system. MonoTrans is an iterative protocol between monolingual people to translate. Monolingual translation, or translation by people who speak only the source or the target language, can be used to solve the problem of translating between rare languages, or to achieve quality translation at a large scale.
A list of my projects is below:
MonoTrans Widgets: Deploying to the Real World
The MonoTrans Widgets system is the first attempt to deploy such a system "in the wild". We found out that drawing from two crowds with different expertise poses unique problems in the design of such crowd-sourcing systems.
Chang Hu, Philip Resnik, Yakov Kronrod, Benjamin B. Bederson. Deploying MonoTrans Widgets in the Wild, To appear on CHI 2012, Sep 2011 [link]
MonoTrans2: Asynchronous Protocol
MonoTrans2 is an improvement on MonoTrans with an asynchronous protocol. As reflected by the design of MonoTrans2, tasks in a translation process can be designed so every user can perform a task independent of the others. The tasks can be broken down and shortened so there is always a task for any user. By introducing these independent short tasks, the synchronicity restriction f or monolingual translation can be removed, which in turn improves the scalability for monolingual translation.
Chang Hu, Philip Resnik, Yakov Kronrod, Vladimir Eidelman, Olivia Buzek, Benjamin B. Bederson. The Value of Monolingual Crowdsourcing in a Real-World Translation Scenario: Simulation using Haitian Creole Emergency SMS Messages. , EMNLP 2011 Sixth Workshop on Statistical Machine Translation, July 2011 [pdf]
Chang Hu, Benjamin B. Bederson, Philip Resnik, Yakov Kronrod. MonoTrans2: A New Human Computation System to Support Monolingual Translation, CHI 2011, May 2011 [DOI]
MonoTrans: Collaborative Translation by Monolingual People
MonoTrans is an iterative protocol between monolingual people to translate. Monolingual translation, or translation by people who speak only the source or the target language, can be used to solve the problem of translating between rare languages, or to achieve quality translation at a large scale. At the core of monolingual translation are protocols in which the human participants (monolingual source or target language speakers) work together to make sense of machine translations. Since monolingual translation does not depend on bilingual humans, it can enable translation between uncommon language pairs where a bilingual translator is hard to find. In addition, monolingual translation can be supported by a larger population, and thus is likely to result in much higher throughput.
Visual Snippets: Summarzing Web Pages Visually
People regularly interact with different representations of Web pages. A person looking for new information may initially find a Web page represented as a short snippet rendered by a search engine. When he wants to return to the same page the next day, the page may instead be represented by a link in his browser history. Previous research has explored how to best represent Web pages in support of specific task types, but, as we find in this paper, consistency in representation across tasks is also important. We explore how different representations are used in a variety of contexts and present a compact representation that supports both the identification of new, relevant Web pages and the re-finding of previously viewed pages.
Jaime Teevan, Edward Curtell, Danyel Fisher, Steven M. Drucker, Gonzalo Ramos, Paul André, Chang Hu. Visual Snippets:Summarizing Web Pages for Search and Revisitation, CHI '09, April 2009 [pdf] [DOI].
POEMS: Paper-Based Screen Control
As more and more tools are developed for meeting support tasks, properly using these tools to get expected results becomes too complicated for many meeting participants. To address this problem, we propose POEMS (Paper Offered Environment Management Service) that allows meeting participants to control services in a meeting environment through a digital pen and an environment photo on digital paper. Unlike state-of-the-art device control interfaces that require interaction with text commands, buttons, or other artificial symbols, our photo enabled service access is more intuitive. Compared with PC and PDA supported control, this new approach is more flexible and cheap. With this system, a meeting participant can initiate a whiteboard on a selected public display by tapping the display image in the photo, or print out a display by drawing a line from the display image to a printer image in the photo. The user can also control video or other active applications on a display by drawing a link between a printed controller and the image of the display. This paper presents the system architecture, implementation tradeoffs, and various meeting control scenarios.
Locating Text in Scanned Books
We describe a work flow to extract and verify text locations using commercial software, along with free software products and human proofing. To help mid-sized digital libraries, we are making our solution available as open source software.