Input Method
Input method research focuses on improving the efficiency and accuracy of text entry, particularly for complex languages like Chinese. Current efforts center on leveraging large language models (LLMs), often incorporating multimodal architectures and generative approaches, to handle diverse input scenarios including imperfect pinyin, speech-to-text errors, and dialect variations. This research is crucial for enhancing user experience across various applications and improving the robustness of natural language processing systems, particularly in handling real-world noisy input data.
Papers
December 4, 2024
July 5, 2024
November 2, 2023
October 8, 2023
February 14, 2023
June 10, 2022