Generative Input: Towards Next-Generation Input Methods Paradigm

Keyu Ding, Yongcan Wang, Zihang Xu, Zhenzhen Jia, Enhong Chen


Abstract
Since the release of ChatGPT, generative models have achieved tremendous success and become the de facto approach for various NLP tasks. However, its application in the field of input methods remains under-explored. Many neural network approaches have been applied to the construction of Chinese input method engines (IMEs). Previous research often assumed that the input pinyin was correct and focused on Pinyin-to-character (P2C) task, which significantly falls short of meeting users’ demands. Moreover, previous research could not leverage user feedback to optimize the model and provide personalized results. In this study, we propose a novel Generative Input paradigm named GeneInput. It uses prompts to handle all input scenarios and other intelligent auxiliary input functions, optimizing the model with user feedback. The results demonstrate that we have achieved state-of-the-art performance for the first time in the Full-mode Key-sequence to Characters task. GeneInput also includes RLHF-IME, a novel RLHF application framework for input method, that eliminates the need for manual ranking annotations and the performance surpasses GPT-4. Relevant resources have been open-sourced.
Anthology ID:
2024.findings-acl.218
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3658–3669
Language:
URL:
https://aclanthology.org/2024.findings-acl.218
DOI:
10.18653/v1/2024.findings-acl.218
Bibkey:
Cite (ACL):
Keyu Ding, Yongcan Wang, Zihang Xu, Zhenzhen Jia, and Enhong Chen. 2024. Generative Input: Towards Next-Generation Input Methods Paradigm. In Findings of the Association for Computational Linguistics: ACL 2024, pages 3658–3669, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Generative Input: Towards Next-Generation Input Methods Paradigm (Ding et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.218.pdf