# Character-Level Question Answering with Attention

arXiv: https://arxiv.org/abs/1604.00727 · HTML: https://mlsanity.com/paper/1604.00727/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2016.

## Built on by (most cited first, 9 of 9)

- [An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering](https://mlsanity.com/paper/2303.10368/) (2023)
- [2-D SSM: A General Spatial Layer for Visual Transformers](https://mlsanity.com/paper/2306.06635/) (2023)
- [Semantic Structure based Query Graph Prediction for Question Answering over Knowledge Graph](https://mlsanity.com/paper/2204.10194/) (2022)
- [Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training](https://mlsanity.com/paper/2104.08763/) (2021)
- [Incremental Knowledge Based Question Answering](https://mlsanity.com/paper/2101.06938/) (2021)
- [Knowledge Graph Question Answering via SPARQL Silhouette Generation](https://mlsanity.com/paper/2109.09475/) (2021)
- [Knowledge Fusion via Bidirectional Information Aggregation](https://mlsanity.com/paper/2507.08704/) (2025)
- [Towards Collaborative Question Answering: A Preliminary Study](https://mlsanity.com/paper/2201.09708/) (2022)
- [Exploring the State of the Art in Legal QA Systems](https://mlsanity.com/paper/2304.06623/) (2023)

## Abstract (arXiv)

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.