EAGER: Computational Models of Essay Rewritings

自然语言处理(NLP)是智能写作辅导系统的组成部分，它允许系统自动分析学生的写作并提供反馈，帮助学生学习。例如，已经开发了一些方法来自动检测和纠正语法使用错误，并评估学生写作的各个方面。然而，目前的技术并不能为教学生修改作文提供足够的支持。与机械纠错不同，修改背后的理由更难确定。对于草稿中不明确的段落，可能会有多个可能的更改；相反，一个具体的文字更改可能是由于几个可能的潜在原因。该奖项旨在调查自然语言处理方法是否能帮助学生在改写的抽象原则(例如，论文应该有一个明确的论题)和进行修改的特定语境之间建立更具体的联系。该项目的成功将使教育应用程序造福社会。这个项目通过确定学生与修订助理的互动是否使他们能够学习更好的写作--即某些形式的反馈(就感知的目的和变化的范围而言)是否鼓励学生学习进行更有效的修订，来评估修订作为一种教学技术的可行性。更具体地说，该项目朝着三个目标努力：(1)定义一个模式，用于描述在不同重写水平上发生的变化类型。例如，作者可能会添加一个或多个句子来提供证据来支持一篇论文；或者作者可能只会添加一两个词来使短语更精确。(2)在模式的基础上，设计了一个计算模型，用于识别修订中每个更改的目的和范围。这种模式的一个应用是复习助手，当学生尝试不同的复习方案时，它充当试听板的作用。(3)通过实验研究学生与修改写作环境之间的相互作用，模拟各种理想化计算模式的变化。这些实验的发现为开发更好的技术来支持学生学习铺平了道路。

Natural language processing (NLP) is an integral part of an intelligent tutoring system for writing; it allows the system to automatically analyze student writings and provide feedback to help students to learn. For example, methods have been developed to automatically detect and correct grammar usage errors and to assess aspects of student writing. However, current technology does not offer enough support for teaching students to revise their writings. Unlike mechanical error corrections, the rationales behind revisions are harder to determine. There may be multiple possible changes for an unclear passage in a draft; conversely, one specific writing change might be due to several possible underlying reasons. This EAGER award investigates whether NLP methods can help students to learn to make a more concrete connection between the abstract principles of rewriting (e.g., "A paper should have a clear thesis") and the particular contexts in which the revision is carried out. The success of this project would enable educational applications that benefit the society. This project evaluates the viability of revision as a pedagogical technique by determining whether student interactions with the revision assistant enables them to learn to write better -- that is, whether certain forms of the feedback (in terms of the perceived purposes and scopes of changes) encourage students to learn to make more effective revisions. More specifically, the project works toward three objectives: (1) Define a schema for characterizing the types of changes that occur at different levels of the rewriting. For example, the writer might add one or more sentences to provide evidence to support a thesis; or the writer might add just one or two words to make a phrase more precise. (2) Based on the schema, design a computational model for recognizing the purpose and scope of each change within a revision. One application of such a model is a revision assistant that serves as a sounding board for students as they experiment with different revision alternatives. (3) Conduct experiments to study the interactions between students and the revision writing environment in which variations of idealized computational models are simulated. The findings of the experiments pave the way for developing better technologies to support for student learning.