Simple Question Answering by Attentive Convolutional Neural Network

Abstract

This work focuses on answering single-relation factoid questions over Freebase. Each question can acquire the answer from a single fact of form (subject, predicate, object) in Freebase. This task, simple question answering (SimpleQA), can be addressed via a two-step pipeline: entity linking and fact selection. In fact selection, we match the subject entity in a fact candidate with the entity mention in the question by a character-level convolutional neural network (char-CNN), and match the predicate in that fact with the question by a word-level CNN (word-CNN). This work makes two main contributions. (i) A simple and effective entity linker over Freebase is proposed. Our entity linker outperforms the state-of-the-art entity linker over SimpleQA task. (ii) A novel attentive maxpooling is stacked over word-CNN, so that the predicate representation can be matched with the predicate-focused question representation more effectively. Experiments show that our system sets new state-of-the-art in this task.

Accepted as an oral long paper by COLING'2016

References in corpus (8)

• Large-scale Simple Question Answering with Memory Networks
• Deep Learning for Answer Sentence Selection
• Attentive Pooling Networks
• Question Answering with Subgraph Embeddings
• Character-Level Question Answering with Attention
• CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases
• On the Generalization Error Bounds of Neural Networks under Diversity-Inducing Mutual Angular Regularization
• Question Answering on Freebase via Relation Extraction and Textual Evidence

Cited by in corpus (6)

• Question Answering over Freebase via Attentive RNN with Similarity Matrix based CNN
• Fast Linear Model for Knowledge Graph Embeddings
• Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications
• No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering "Simple" Questions)
• Using Context Information to Enhance Simple Question Answering
• The combination of context information to enhance simple question answering