Question Answering with Subgraph Embeddings

Abstract

This paper presents a system which learns to answer questions on a broad range of topics from a knowledge base using few hand-crafted features. Our model learns low-dimensional embeddings of words and knowledge base constituents; these representations are used to score natural language questions against candidate answers. Training our system using pairs of questions and structured representations of their answers, and pairs of question paraphrases, yields competitive results on a competitive benchmark of the literature.

References in corpus (2)

• HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
• Open Question Answering with Weakly Supervised Embedding Models

Cited by in corpus (57)

• Deep Learning for Answer Sentence Selection
• Natural Language Processing Advancements By Deep Learning: A Survey
• Differentiable Learning of Logical Rules for Knowledge Base Reasoning
• Towards Universal Paraphrastic Sentence Embeddings
• Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering
• Traversing Knowledge Graphs in Vector Space
• An Interpretable Reasoning Network for Multi-Relation Question Answering
• Explicit Knowledge-based Reasoning for Visual Question Answering
• Character-Level Question Answering with Attention
• Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
• Extraction of Salient Sentences from Labelled Documents
• On the representation and embedding of knowledge bases beyond binary relations
• Visual Madlibs: Fill in the blank Image Generation and Question Answering
• Neural Programmer: Inducing Latent Programs with Gradient Descent
• Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems
• Neural Information Retrieval: A Literature Review
• Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information
• FVQA: Fact-based Visual Question Answering
• Learning from Few Samples: A Survey
• Fast Linear Model for Knowledge Graph Embeddings
• Simple Question Answering by Attentive Convolutional Neural Network
• Simpler Context-Dependent Logical Forms via Model Projections
• Inferring Missing Entity Type Instances for Knowledge Base Completion: New Dataset and Methods
• Learning Structured Natural Language Representations for Semantic Parsing
• Question Answering on Freebase via Relation Extraction and Textual Evidence
• Freebase-triples: A Methodology for Processing the Freebase Data Dumps
• Learning Visual Knowledge Memory Networks for Visual Question Answering
• Learning to Understand Phrases by Embedding the Dictionary
• No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering "Simple" Questions)
• Layer-Parallel Training of Deep Residual Neural Networks
• LSTM-based Mixture-of-Experts for Knowledge-Aware Dialogues
• Toward a Deep Neural Approach for Knowledge-Based IR
• Adversarial Learning for Debiasing Knowledge Graph Embeddings
• Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables
• Adaptive Margin Ranking Loss for Knowledge Graph Embeddings via a Correntropy Objective Function
• Knowledge Based Machine Reading Comprehension
• Analogs of Linguistic Structure in Deep Representations
• Weakly-supervised Neural Semantic Parsing with a Generative Ranker
• Learning an Executable Neural Semantic Parser
• Embedding Words and Senses Together via Joint Knowledge-Enhanced Training
• Graph Pattern Entity Ranking Model for Knowledge Graph Completion
• Binarized Knowledge Graph Embeddings
• Visual Question Answering as Reading Comprehension
• Learning to Answer Ambiguous Questions with Knowledge Graph
• Convolutional Hypercomplex Embeddings for Link Prediction
• AliMe KBQA: Question Answering over Structured Knowledge for E-commerce Customer Service
• Out-of-Vocabulary Embedding Imputation with Grounded Language Information by Graph Convolutional Networks
• Recent Advances in Automated Question Answering In Biomedical Domain
• Data Collection for Interactive Learning through the Dialog
• Accurate and Energy-Efficient Classification with Spiking Random Neural Network: Corrected and Expanded Version
• Multiple Instance Learning Convolutional Neural Networks for Object Recognition
• DRILL-- Deep Reinforcement Learning for Refinement Operators in $\mathcal{A}\mathcal{LC}$
• Task-specific Word Identification from Short Texts Using a Convolutional Neural Network
• The combination of context information to enhance simple question answering
• Learning Solving Procedure for Artificial Neural Network
• Hierarchical Attention Model for Improved Machine Comprehension of Spoken Content
• Navigation-Based Candidate Expansion and Pretrained Language Models for Citation Recommendation