2023 MJIC Winner

BETTER INTEGRATION OF AI MODELS INTO TRANSLATION TOOLS

Computer-Assisted Translation (CAT) tools have emerged as the go-to solution for professional translators, setting the industry standard. These tools revolutionize the translation process by seamlessly integrating comprehensive databases of prior translation fragments and incorporating machine-generated translations. By doing so, CAT tools have proven their ability to significantly enhance a translator’s workflow, leading to increased efficiency and productivity. However, it is important to note that while these tools offer remarkable advantages, they often fall short when it comes to leveraging contextual information effectively. In contrast, the advent of advanced AI models, such as ChatGPT, has opened up new possibilities in the field of translation. These AI models possess the capability to exploit contextual cues, thereby potentially enhancing the accuracy and quality of translations. The immense potential of AI in translation has sparked our project’s focus on seamlessly integrating these powerful AI models into existing translation tools, with the ultimate aim of creating innovative and novel translation tools that can better assist and accelerate the work of human translators.

By harnessing the strengths of CAT tools and AI models, we strive to strike a balance between efficiency and accuracy in translation. Our project aims to overcome the limitations of static machine-generated translations by leveraging the contextual understanding abilities of AI models like ChatGPT. This integration will empower translators to access a comprehensive array of translation fragments and take advantage of the contextual nuances that are crucial for producing accurate and natural translations.

Through our research and development efforts, we endeavor to bridge the gap between the speed offered by CAT tools and the contextual comprehension offered by AI models. By seamlessly integrating these technologies, we hope to empower translators with a powerful suite of translation tools that can not only streamline their workflow but also improve the overall translation quality. Our project stands at the forefront of the translation industry, driving innovation and pushing the boundaries of what is possible in the realm of computer-assisted translation.

Winning Team

William Chen is a graduate student at Carnegie Mellon University (CMU) in Pittsburgh, PA, USA. He is advised by Dr. Shinji Watanabe at the Language Technologies Institute and was recently a visiting scholar at NTT Japan.

His research collaborators have included Meta, MIT, Columbia University, and National Taiwan University. He received his B.S. in Computer Science and B.A. in History from the University of Central Florida. Prior to joining CMU, he was a software engineer at Texas Instruments.

Chih-Chen Chen is a skilled Taiwanese translator with a passion for bridging linguistic and cultural gaps. With expertise in both English and Mandarin Chinese, Chen Chih-Chen possesses the remarkable ability to seamlessly convey meaning and nuance across languages. As a dedicated language professional, Chen Chih-Chen has honed their translation skills through extensive experience and a deep understanding of the intricacies of both Taiwanese and Western cultures. Whether it’s translating business documents, literary works, or legal texts, Chen Chih-Chen’s meticulous attention to detail and commitment to accuracy make them a trusted and reliable language partner.