arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.01166cs.CLcs.AI
收藏

生成式输入:迈向下一代输入法范式

Generative Input: Towards Next-Generation Input Methods Paradigm

University of Science and Technology of China(中国科学技术大学);State Key Laboratory of Cognitive Intelligence, iFLYTEK Research(认知智能国家重点实验室,科大讯飞研究院);iFLYTEK AI Research(科大讯飞人工智能研究院)

Keyu Ding, Yongcan Wang, Zihang Xu, Zhenzhen Jia, Shijin Wang, Cong Liu, Enhong Chen

AI总结:

本文提出生成式输入范式GeneInput,通过提示统一处理输入场景并利用用户反馈实现个性化,首次在FK2C任务上达到最优性能,并在智能联想与对话辅助上超越GPT-4。

摘要:

自ChatGPT发布以来,生成模型取得了巨大成功,并成为各类自然语言处理任务的事实标准方法。然而,其在输入法领域的应用仍未得到充分探索。许多神经网络方法已被应用于中文输入法引擎(IME)的构建中。以往研究通常假设输入的拼音是正确的,并聚焦于拼音到汉字(P2C)任务,这远远无法满足用户需求。此外,以往研究无法利用用户反馈来优化模型并提供个性化结果。在本研究中,我们提出了一种新颖的生成式输入范式,命名为GeneInput。它使用提示来处理所有输入场景及其他智能辅助输入功能,并利用用户反馈优化模型以提供个性化结果。实验结果表明,我们首次在全模式按键序列到字符(FK2C)任务上取得了最先进的性能。我们提出了一种新颖的奖励模型训练方法,无需额外的人工标注,并且在智能联想和对话辅助任务中的表现超越了GPT-4。与传统范式相比,GeneInput不仅展现出更优越的性能,还表现出更强的鲁棒性、可扩展性和在线学习能力。

英文摘要:

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 to deliver personalized results. The results demonstrate that we have achieved state-of-the-art performance for the first time in the Full-mode Key-sequence to Characters(FK2C) task. We propose a novel reward model training method that eliminates the need for additional manual annotations and the performance surpasses GPT-4 in tasks involving intelligent association and conversational assistance. Compared to traditional paradigms, GeneInput not only demonstrates superior performance but also exhibits enhanced robustness, scalability, and online learning capabilities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑