Skipping Word: A Character-Sequential Representation based Framework for Question Answering
This addresses efficiency and stability issues in question answering systems, though it appears incremental as it builds on existing character-level and CNN approaches.
The paper tackles the problem of corpus selection and dictionary transformation in word embedding-based question answering by proposing a character-sequential representation framework using convolutional neural networks, achieving competitive performance on two benchmark datasets.
Recent works using artificial neural networks based on word distributed representation greatly boost the performance of various natural language learning tasks, especially question answering. Though, they also carry along with some attendant problems, such as corpus selection for embedding learning, dictionary transformation for different learning tasks, etc. In this paper, we propose to straightforwardly model sentences by means of character sequences, and then utilize convolutional neural networks to integrate character embedding learning together with point-wise answer selection training. Compared with deep models pre-trained on word embedding (WE) strategy, our character-sequential representation (CSR) based method shows a much simpler procedure and more stable performance across different benchmarks. Extensive experiments on two benchmark answer selection datasets exhibit the competitive performance compared with the state-of-the-art methods.