Character-Level Question Answering with Attention
This work addresses efficient and robust question answering for structured knowledge bases, with incremental improvements in accuracy and model size.
The paper tackles question answering with a knowledge base by applying a character-level encoder-decoder framework, achieving a state-of-the-art accuracy improvement from 63.9% to 70.9% on the SimpleQuestions dataset while using 16x fewer parameters and less data than previous methods.
We show that a character-level encoder-decoder framework can be successfully applied to question answering with a structured knowledge base. We use our model for single-relation question answering and demonstrate the effectiveness of our approach on the SimpleQuestions 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.