YNU-HPCC at IJCNLP-2017 Task 5: Multi-choice Question Answering in Exams Using an Attention-based LSTM Model

摘要

A shared task is a typical question answering task that aims to test how accurately the participants can answer the question-s in exams. Typically, for each question, there are four candidate answers, and only one of the answers is correct. The existing methods for such a task usually implement a recurrent neural network (RNN) or long short-term memory (LSTM). However, both RNN and LSTM are biased models in which the words in the tail of a sentence are more dominant than the words in the header. In this paper, we propose the use of an attention-based LSTM (AT-LSTM) model for these tasks. By adding an attention mechanism to the standard L-STM, this model can more easily capture long contextual information. Our submission ranked first among 35 teams in terms of the accuracy at the IJCNLP-2017 multi-choice question answering in Exams for all datasets.