用3个按键搭配大模型，实现接近常规输入的文本输入效果。
3-Key-Input: Exploring the Theoretical Minimum Keys for Text Entry
- 仅用3个物理键+语言模型解歧，实现高效文本输入。
- 3键搭配GPT-4o时，字符错误率降至9.46%，比2键降低59%。
- 技术类文本错误率是商务类的两倍，适合残障设备等场景。
本文系统评估了使用2至5个物理键结合语言模型进行文本输入的效果。在包含300句英文（每类100句：商务、对话、技术）的语料上，对比不同按键数量、字母映射方式（布局/频率/故意最差）及解码器（仅字典、GPT-2束搜索、GPT-4o选择）。结果表明，3键+GPT-4o可实现9.46%的字符错误率（CER）和12.20%的词错误率（WER），相较2键（CER 23.3%）降低59%。3键时每字符信息熵为1.54比特；增至5键后CER降至5.4%，但边际收益递减。映射方式影响较小（ΔCER < 0.5个百分点），即使故意设计最差映射也仅增加0.5个百分点误差。技术类文本错误率约为商务类的两倍。在强语言模型先验下，3键是通用英文输入的实际最小值。
原文摘要 · Abstract (English)
How far can we reduce the number of physical keys if we endow an ambiguous keyboard with modern language models? Fewer keys increase hardware design freedom in constrained settings such as assistive devices and mobile form factors. This paper systematically evaluates text entry systems using 2-5 physical keys combined with language-model-based disambiguation. On a 300-sentence English corpus (100 sentences each for Business / Conversational / Technical), we compare key counts (2-5), letter-to-key mappings (layout-based / frequency-based / intentionally worst-case), and decoders (Trie-only, GPT-2 beam search, GPT-4o selection). We find that 3 keys + GPT-4o achieves character error rate (CER) 9.46% and word error rate (WER) 12.20%, reducing CER by 59% relative to 2 keys (CER 23.3%). At 3 keys, the key-stream entropy is 1.54 bits/char; while increasing to 5 keys improves accuracy (CER 5.4%), the marginal gains diminish. Mapping choice has a small impact under standard designs (ΔCER < 0.5 pp), and even an intentionally worst mapping degrades CER by only +0.5 pp, whereas Technical sentences yield roughly twice the error rate of Business. These results suggest that, in our evaluated offline setting under a strong LM prior, 3 keys are a practical minimum for general English.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。