Character-Level Question Answering with Attention

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.

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Large-scale Simple Question Answering with Memory Networks
• Text Understanding from Scratch
• Learning to Execute
• Question Answering with Subgraph Embeddings

Cited by in corpus (31)

• Improved Neural Relation Detection for Knowledge Base Question Answering
• Exploring the State of the Art in Legal QA Systems
• Question Answering over Freebase via Attentive RNN with Similarity Matrix based CNN
• Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs
• Fast Linear Model for Knowledge Graph Embeddings
• Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training
• Simple Question Answering by Attentive Convolutional Neural Network
• Compositionality decomposed: how do neural networks generalise?
• Knowledge Graph-based Question Answering with Electronic Health Records
• An Attention-Based Word-Level Interaction Model: Relation Detection for Knowledge Base Question Answering
• End-to-End Entity Linking and Disambiguation leveraging Word and Knowledge Graph Embeddings
• No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering "Simple" Questions)
• Revisiting the Hierarchical Multiscale LSTM
• A General FOFE-net Framework for Simple and Effective Question Answering over Knowledge Bases
• Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• ParaCNN: Visual Paragraph Generation via Adversarial Twin Contextual CNNs
• Exploring Different Dimensions of Attention for Uncertainty Detection
• Knowledge Base Relation Detection via Multi-View Matching
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
• Knowledge Graph Question Answering via SPARQL Silhouette Generation
• Gradual Machine Learning for Aspect-level Sentiment Analysis
• Seq2Seq and Multi-Task Learning for joint intent and content extraction for domain specific interpreters
• Learning to Answer Ambiguous Questions with Knowledge Graph
• Neural Relation Prediction for Simple Question Answering over Knowledge Graph
• Nonsymbolic Text Representation
• Less is More: Data-Efficient Complex Question Answering over Knowledge Bases
• Pretrained Transformers for Simple Question Answering over Knowledge Graphs
• Incremental Knowledge Based Question Answering
• The combination of context information to enhance simple question answering
• A Knowledge Graph Based Solution for Entity Discovery and Linking in Open-Domain Questions
• Using Context Information to Enhance Simple Question Answering