Large-scale Simple Question Answering with Memory Networks

Abstract

Training large-scale question answering systems is complicated because training sources usually cover a small portion of the range of possible questions. This paper studies the impact of multitask and transfer learning for simple question answering; a setting for which the reasoning required to answer is quite easy, as long as one can retrieve the correct evidence given a question, which can be difficult in large-scale conditions. To this end, we introduce a new dataset of 100k questions that we use in conjunction with existing benchmarks. We conduct our study within the framework of Memory Networks (Weston et al., 2015) because this perspective allows us to eventually scale up to more complex reasoning, and show that Memory Networks can be successfully trained to achieve excellent performance.

Cited by in corpus (71)

• The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
• Learning to Remember Rare Events
• A Neural Knowledge Language Model
• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
• Representation Learning for Natural Language Processing
• Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering
• Automatic Rule Extraction from Long Short Term Memory Networks
• Improved Neural Relation Detection for Knowledge Base Question Answering
• A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges
• UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering
• Visual Question Answering: A Survey of Methods and Datasets
• Towards Transparent AI Systems: Interpreting Visual Question Answering Models
• Dynamically Fused Graph Network for Multi-hop Reasoning
• Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs
• Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks
• Learning from Few Samples: A Survey
• Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering
• Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
• Fast Linear Model for Knowledge Graph Embeddings
• Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications
• CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases
• IQA: Interactive Query Construction in Semantic Question Answering Systems
• Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering
• Question Answering from Unstructured Text by Retrieval and Comprehension
• TableQA: a Large-Scale Chinese Text-to-SQL Dataset for Table-Aware SQL Generation
• A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions
• Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning
• Sentence Embedding Alignment for Lifelong Relation Extraction
• End-to-End Entity Linking and Disambiguation leveraging Word and Knowledge Graph Embeddings
• An Attention-Based Word-Level Interaction Model: Relation Detection for Knowledge Base Question Answering
• OneStop QAMaker: Extract Question-Answer Pairs from Text in a One-Stop Approach
• Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases
• Hierarchical Memory Networks for Answer Selection on Unknown Words
• A General FOFE-net Framework for Simple and Effective Question Answering over Knowledge Bases
• Multimodal Memory Modelling for Video Captioning
• Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering
• Teaching Machines to Converse
• Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering
• Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
• Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering
• SYGMA: System for Generalizable Modular Question Answering OverKnowledge Bases
• GlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph
• Knowledge Graph Embedding with Multiple Relation Projections
• Revisiting the Open-Domain Question Answering Pipeline
• JEC-QA: A Legal-Domain Question Answering Dataset
• Knowledge Graph Question Answering via SPARQL Silhouette Generation
• Curriculum-Meta Learning for Order-Robust Continual Relation Extraction
• Dynamic Key-Value Memory Networks for Knowledge Tracing
• Learning to Answer Ambiguous Questions with Knowledge Graph
• De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention
• Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning
• Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction
• VANiLLa : Verbalized Answers in Natural Language at Large Scale
• Pretrained Transformers for Simple Question Answering over Knowledge Graphs
• MK-SQuIT: Synthesizing Questions using Iterative Template-filling
• Hierarchical Attention Model for Improved Machine Comprehension of Spoken Content
• Less is More: Data-Efficient Complex Question Answering over Knowledge Bases
• Where is Linked Data in Question Answering over Linked Data?
• End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs
• Knowledge Graph Simple Question Answering for Unseen Domains
• Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning
• Exploiting Rich Syntax for Better Knowledge Base Question Answering
• Question Answering over Knowledge Graphs with Neural Machine Translation and Entity Linking
• A Knowledge-based Approach for Answering Complex Questions in Persian
• Using Context Information to Enhance Simple Question Answering
• Document Similarity for Texts of Varying Lengths via Hidden Topics
• Timestamping Documents and Beliefs
• Memory networks for consumer protection:unfairness exposed
• Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss
• Incremental Knowledge Based Question Answering
• Modeling Global Semantics for Question Answering over Knowledge Bases