San Jose, CA (Nov 13, 2023) – XL8, a leading deep-tech startup specializing in AI-powered machine translation technology, has made a significant contribution to the field of natural language processing (NLP) by submitting a noteworthy paper to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), one of the world’s premier conferences for NLP. Their paper, titled “Enhanced Simultaneous Machine Translation with Word-level Policies,” authored by Research Scientists Kai Kang Kim and Matthew Hankyu Cho, both of whom contributed equally to the work, was accepted for publication in the upcoming EMNLP 2023 Findings in December.
This research paper introduces an innovative method aimed at enhancing the performance of Simultaneous Machine Translation (SiMT). The key innovation presented is the incorporation of word-level policies into real-time translation systems, departing from the traditional practice of using subword-level policies.
Typically, Machine Translation models segment words into subwords for various advantages like flexibility in modeling and handling rare words. For SiMT models, which operate under a policy that determines when to receive remaining input words or resume translation, previous approaches relied on policies that worked at the subword level.
However, a subword-level policy often produces translations from partially processed input words before all of their subwords are processed, resulting in suboptimal translation quality. Moreover, it hinders the integration of a language model (LM), which has been proven to be a powerful method for enhancing many NLP tasks, due to the subword mismatch between the LM and SiMT.
This study demonstrates that by adopting the proposed word-level policies, it is possible to address these limitations and achieve more accurate results with lower latency, hence significantly improving real-time translation performance.
The real-time translation model developed through this research has already been seamlessly integrated into EventCAT, an advanced real-time translation and interpretation service offered by XL8.
With XL8’s EventCAT, you can elevate the accessibility and inclusivity of your live broadcasts and event streams while providing a superior user experience. It also generates on-screen translated text and synthetic speech, enabling multilingual conversations for global call centers, conferences, international meetings, or video calls.
Notably, EventCAT has played a pivotal role in offering mobile translation services in multiple languages, such as English, Arabic, and Chinese, at various domestic and international events like Nature Forum, Leeum Art Museum’s Special Event, ComeUp2023, and Content Universe Korea. This integration has transformed the event experience, enabling participants to fully immerse themselves in the content, regardless of language barriers.
About XL8
XL8 was founded in 2019 by technical executives from Google and Apple, both with an advanced degree in Computer Science from Columbia University. A Silicon Valley tech company at its core, XL8 takes AI-powered machine translation (MT), specially optimized for media content, to the next level. Its advanced technology allows significantly more efficient workflows by providing: in-line editing, automated media transcription with time coding, automated subtitling, synthesized voice dubbing, real-time meeting interpretation, and live subtitling. XL8’s uniquely specialized translation engines have been built from the ground up utilizing professionally trained, human-perfected subtitles curated from the media industry’s top content producers. XL8’s “secret sauce” offers media-focused translation accuracy that is up to 40% higher than other generally available MT services. Since its inception, XL8 has surpassed translating 800,000 hours of content and more than 2.2 billion words and currently supports more than 45 tier 1 languages.
For more information, please visit http://xl8.ai
For more information, contact:
USA: Season Skuro, +1-818-903-8205 / [email protected]
UK: Shawn Belluigi, +44 (0) 7754 553 798 / [email protected]
