A Multilingual Chat System with Image Presentation for Detecting Mistranslation

Abstract

We have designed and developed a multilingual chat system, MCHI (Multilingual Chat with Hint Images), which is based on machine translation and equipped with a presentation function of images related to the contents of the messages by utterers so that listeners are able to notice mistranslation. MCHI accepts English, French, Chinese, Japanese, Korean and Vietnamese languages. It uses the Google API to retrieve related images from the image posting site Flickr. As a result of evaluation experiment, we have observed that participants detected the mismatch of a translated message with its related image. According to the answers of participants for a questionnaire, it turned out that the usability of the MCHI system is good enough though the related images are not satisfactory.

Can Graphical Interaction Increase Feelings of Conveying and Understanding in On-Line Group Discussion?

“…To support multilingual chat, Hosogai et al developed the multilingual chat with helpful images (MCHI) system [12]. Traditional multilingual text chat systems that use machine translation have a problem when listeners cannot detect system mistranslations.…”

“…Even though past research work developed a function to dis- play images related to nouns contained in text communication [12], it did not provide the graphical function to display nouns and corresponding images together. We thought that this function would reduce the burden of representing users' interpretations.…”

“…However, such repetitive exchanges of text messages are troublesome for users in text chat. To reduce the redundancy of such communication, researchers developed graphical text chat systems that display images related to text messages [11], [12], [14].…”