Embodiments herein provide automated assessment of examination scripts, such as English for Speakers of Other Languages (ESOL) examination scripts, written in response to prompts eliciting free text answers. In an embodiment, the task may be defined as discriminative preference ranking. Further, a system employing such methodology may be trained and tested on a corpus of manually-graded scripts. Embodiments herein, unlike extant solutions, are relatively prompt-insensitive and resistant to subversion, even if the operating principles are known. Embodiments may also detect scripts which are linguistically good but non-responsive to prompts such as memorized responses.
展开▼
