An Exploratory System to Teach English as a Second Language to Deaf Students with American Sign Language Competency

向具有美国手语能力的聋哑学生教授英语作为第二语言的探索性系统

• 批准号: 9416916
• 负责人: Kathleen McCoy
• 金额: $ 23.98万
• 依托单位: University of Delaware
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1995
• 资助国家: 美国
• 起止时间: 1995-04-15 至 1999-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9416916&HistoricalAwards=false
• 关键词: Exploratory; System; Teach; English; Second

The long term goal of this work is to develop a writing tool for native users of American Sign Language (ASL). Envisioned is a computer system that will take a piece of text written by a deaf user, analyze that text for errors, engage that user in a tutorial dialogue, and generate appropriate corrections to the text. Some of the necessary foundation for the envisioned system are laid. One area of interest is the detection and correction of discourse structuring and cohesion errors. Emphasis is on errors involving reference to items previously introduced in the discourse. Because there is evidence that many of the writing errors found are attributable to transfering strategies from ASL to English, reference to ASL in the correction may be beneficial. This requires a flexible correction system design which is able modularly alter the content and form of a correction strategy. Feedback is tailored to the needs, preferences, and abilities of each individual user. This is achieved through the development of a linguistically motivated user model to track the user's acquisition of English, and a sen tence generator which is able to tailor its output to the various levels of acquisition.

这项工作的长期目标是为美国手语（ASL）的本地用户开发一个写作工具。 设想的是一个计算机系统，它将采取一个聋人用户写的一段文本，分析该文本的错误，使该用户参与教程对话，并生成适当的更正文本。 为设想的系统奠定了一些必要的基础。 语篇结构和衔接错误的发现和纠正是一个很有意义的领域。 重点是错误涉及的项目之前介绍的话语。 因为有证据表明，许多写作错误是由于从美国手语迁移到英语的策略，参考美国手语在纠正可能是有益的。 这需要灵活的校正系统设计，其能够模块化地改变校正策略的内容和形式。 反馈是根据每个用户的需求、偏好和能力定制的。这是通过开发一个语言动机的用户模型来跟踪用户对英语的习得，以及一个句子生成器来实现的，该生成器能够根据不同的习得水平来调整其输出。