Open Question Answering with Weakly Supervised Embedding Models

Abstract

Building computers able to answer questions on any subject is a long standing goal of artificial intelligence. Promising progress has recently been achieved by methods that learn to map questions to logical forms or database queries. Such approaches can be effective but at the cost of either large amounts of human-labeled data or by defining lexicons and grammars tailored by practitioners. In this paper, we instead take the radical approach of learning to map questions to vectorial feature representations. By mapping answers into the same space one can query any knowledge base independent of its schema, without requiring any grammar or lexicon. Our method is trained with a new optimization procedure combining stochastic gradient descent followed by a fine-tuning step using the weak supervision provided by blending automatically and collaboratively generated resources. We empirically demonstrate that our model can capture meaningful signals from its noisy supervision leading to major improvements over paralex, the only existing method able to be trained on similar weakly labeled data.

References in corpus (2)

• Natural Language Processing (almost) from Scratch
• HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent

Cited by in corpus (24)

• Recent Trends in Deep Learning Based Natural Language Processing
• Deep Learning for Answer Sentence Selection
• Question Answering with Subgraph Embeddings
• An Interpretable Reasoning Network for Multi-Relation Question Answering
• Visual Madlibs: Fill in the blank Image Generation and Question Answering
• Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering
• Knowledge Graph Completion via Complex Tensor Factorization
• Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information
• FVQA: Fact-based Visual Question Answering
• Neural Generative Question Answering
• Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks
• Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering
• Question Answering over Knowledge Base using Language Model Embeddings
• Dual Ask-Answer Network for Machine Reading Comprehension
• An Attention-Based Word-Level Interaction Model: Relation Detection for Knowledge Base Question Answering
• Deep Style Match for Complementary Recommendation
• Automatic Generation of Grounded Visual Questions
• Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment
• Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables
• Embedding Uncertain Knowledge Graphs
• Recent Advances in Automated Question Answering In Biomedical Domain
• A Probabilistic Framework for Knowledge Graph Data Augmentation
• The combination of context information to enhance simple question answering
• Automatic Question-Answering Using A Deep Similarity Neural Network