One-shot Learning for Question-Answering in Gaokao History Challenge
This work addresses a domain-specific challenge in AI for educational assessment, focusing on question-answering in history exams, but it appears incremental as it builds on existing neural methods.
The authors tackled the problem of answering questions from Chinese university admission exams (Gaokao) in history by proposing a hybrid neural model that uses a cooperative gated neural network and a neural turing machine labeler. The model achieved substantial performance gains over various neural baselines in terms of multiple evaluation metrics.
Answering questions from university admission exams (Gaokao in Chinese) is a challenging AI task since it requires effective representation to capture complicated semantic relations between questions and answers. In this work, we propose a hybrid neural model for deep question-answering task from history examinations. Our model employs a cooperative gated neural network to retrieve answers with the assistance of extra labels given by a neural turing machine labeler. Empirical study shows that the labeler works well with only a small training dataset and the gated mechanism is good at fetching the semantic representation of lengthy answers. Experiments on question answering demonstrate the proposed model obtains substantial performance gains over various neural model baselines in terms of multiple evaluation metrics.