arXiv cs.CL· Zeming Zhao·· 11 小时前AI 评分31
会议口译员零编程自建 CAI 工具：实践生长型工具范式
Growing One's AI Tools: A Paradigm of Practice-Grown Tools
AI 导读
一名未受过编程训练的会议口译员自行开发出计算机辅助口译（CAI）工具，八周内通过 62 次提交迭代出六个版本，记录涵盖 133 次会话、逾 2 万条识别语音。工具在需求出现当天即部署相应能力，一次策略调整在一个下午内将端到端延迟中位数降低超过三分之一。文章据此提出“实践生长型工具”范式，强调从使用工具转向培育工具、工具与实践在故障与修复中共同演化，并给出三项面向工具纳入式从业者评估的命题。
正文 · 原文
Abstract:Professionals have long used software built for them by others. This article reports the growth of a professional computer-assisted interpreting (CAI) tool built by its own user, a conference interpreter without programming training. Drawing on an eight-week version-controlled record with telemetry from 133 logged sessions and over 20,000 recognized utterances, the article traces how real conference work drove the tool through 62 commits and six versions. The record shows capabilities deployed on the day their need appeared and one strategy change that cut median end-to-end delay by over a third within one afternoon. The article then proposes the paradigm of practice-grown tools, defined by the shift from using to growing, the co-evolution of tool and practice through breakdown and repair, bounded local computation, and an assessment corollary, and it formulates three propositions toward tool-inclusive assessment of practitioners, from tool-making literacy to a compute-standardized format for certifying what they and their tools achieve together.
| Comments: | 15 pages, 3 figures, 3 tables, 49 references |
| Subjects: | Human-Computer Interaction (cs.HC); Computation and Language (cs.CL); Software Engineering (cs.SE) |
| Cite as: | arXiv:2611.06132 [cs.HC] |
| (or arXiv:2611.06132v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06132 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zeming Zhao [view email]
[v1]
Wed, 4 Nov 2026 08:15:31 UTC (712 KB)
来源：arXiv cs.CL · arxiv.org