Question Answering with Subgraph Embeddings

2014/06/14 by Antoine Bordes, Sumit Chopra, Bordes, Antoine +3 · 10 citations
Computer Science · #Advanced Graph Neural Networks #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1406.3676

openalex publication_date 2014/06/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent

Cited by

• Keywords are not always the key: A metadata field analysis for natural language search on open data portals
• Towards Universal Paraphrastic Sentence Embeddings
• Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems
• On the representation and embedding of knowledge bases beyond binary relations
• Analogs of Linguistic Structure in Deep Representations
• Simple Question Answering by Attentive Convolutional Neural Network
• Character-Level Question Answering with Attention
• Learning to Answer Ambiguous Questions with Knowledge Graph
• Toward a Deep Neural Approach for Knowledge-Based IR
• Traversing Knowledge Graphs in Vector Space

Related

• Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering
• EEE-QA: Exploring Effective and Efficient Question-Answer Representations
• Learning to answer questions
• Knowledge Base Question Answering by Case-based Reasoning over Subgraphs
• Simple and Effective Semi-Supervised Question Answering