No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering "Simple" Questions)

Abstract

First-order factoid question answering assumes that the question can be answered by a single fact in a knowledge base (KB). While this does not seem like a challenging task, many recent attempts that apply either complex linguistic reasoning or deep neural networks achieve 65%-76% accuracy on benchmark sets. Our approach formulates the task as two machine learning problems: detecting the entities in the question, and classifying the question as one of the relation types in the KB. We train a recurrent neural network to solve each problem. On the SimpleQuestions dataset, our approach yields substantial improvements over previously published results --- even neural networks based on much more complex architectures. The simplicity of our approach also has practical advantages, such as efficiency and modularity, that are valuable especially in an industry setting. In fact, we present a preliminary analysis of the performance of our model on real queries from Comcast's X1 entertainment platform with millions of users every day.

arXiv comment7 pages, to appear in EMNLP 2017

References in corpus (11)

• Natural Language Processing (almost) from Scratch
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Convolutional Neural Networks for Sentence Classification
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
• Large-scale Simple Question Answering with Memory Networks
• Question Answering with Subgraph Embeddings
• Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network
• Character-Level Question Answering with Attention
• Simple Question Answering by Attentive Convolutional Neural Network
• Recurrent Neural Network Encoder with Attention for Community Question Answering

Cited by in corpus (4)

• Learning Structured Natural Language Representations for Semantic Parsing
• Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks
• Using Context Information to Enhance Simple Question Answering
• The combination of context information to enhance simple question answering