Character-Level Question Answering with Attention

TL;DR

This paper presents a character-level encoder-decoder model for question answering over structured knowledge bases, achieving high accuracy with fewer parameters and less data, and demonstrating robustness to new entities.

Contribution

The authors introduce a character-level approach for question answering that outperforms previous models in accuracy, parameter efficiency, and data requirements.

Findings

Achieved 70.9% accuracy on SimpleQuestions dataset.

Model has 16x fewer parameters than word-level counterparts.

Robust to new entities in testing data.

Abstract

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.