近五十年来自动评分研究综述——兼论中国学生英译汉机器评分系统的新探索

Rethinking 50 Years of Studies on Automated Scoring —Explorations of Computer Scoring System for English-Chinese Translations of Chinese Learners

近五十年来，国内外相继开发出多个英语作文自动评分系统，研究日臻成熟。在翻译领域，自动评分研究主要局限于机器翻译评价，人工译文自动评分研究仍处于初级阶段。近年国内建立起针对中国学生的汉译英自动评分模型，针对英译汉的自动评分研究也开始起步。由于中国学生的英译汉具有自身的特点，其评分系统在变量挖掘、模型验证等方面与已有研究不同。

In the past 50 years a number of automated English essay scoring systems have been developed at home and abroad, so research along this line has matured. However, previous attempts to automate the scoring process of translation focused on machine translation and research dealing with human translation is very rudimentary. In recent years scoring models for Chinese students’ Chinese-English (C-E) translations have been constructed and a system handling English-Chinese (E-C) translations is also taking the initial step. Since the E-C translations of Chinese learners have unique features, the scoring system is different from previous studies in many aspects, such as variable mining and model validation.