Character-Level Question Answering with Attention
Xiaodong He, David B. Golub · 2016
We show that a character-level encoderdecoder framework can be successfully applied to question answering with a structured knowledge base.We use our model for singlerelation question answering and demonstrate the effectiveness of our approach on the Sim-pleQuestions dataset (Bordes et al., 2015), where we improve state-of-the-art accuracy from 63.9% to 70.9%, without use of ensembles.Importantly, our character-level model has 16x fewer parameters than an equivalent word-level model, can be learned with significantly less data compared to previous work, which relies on data augmentation, and is robust to new entities in testing. 1