litlas
Log inCreate account

Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks

Authors: Jason Weston, Antoine Bordes, Sumit Chopra, Alexander M. Rush, Bart van Merriënboer, Armand Joulin, Tomáš Mikolov - International Conference on Learning Representations, ICLR 2016 cited by 758

Abstract: One long-term goal of machine learning research is to produce methods that are applicable to reasoning and natural language, in particular building an intelligent dialogue agent. To measure progress towards that goal, we argue for the usefulness of a set of proxy tasks that evaluate reading comprehension via question answering. Our tasks measure understanding in several ways: whether a system is able to answer questions via chaining facts, simple induction, deduction and many more. The tasks are designed to be prerequisites for any system that aims to be capable of conversing with a human. We believe many existing learning systems can currently not solve them, and hence our aim is to classify these tasks into skill sets, so that researchers can identify (and then rectify) the failings of their systems. We also extend and improve the recently introduced Memory Networks model, and show it is able to solve some, but not all, of the tasks.

Long Short-Term MemoryLong Short-Term MemoryUCI Machine LearningRepositoryUCI Machine Learning RepositoryThe Winograd SchemaChallengeThe Winograd Schema ChallengeMCTest: A ChallengeDataset for the…MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of TextMemory NetworksMemory NetworksSequence to SequenceLearning with Neural…Sequence to Sequence Learning with Neural NetworksNeural Turing MachinesNeural Turing MachinesModeling BiologicalProcesses for Reading…Modeling Biological Processes for Reading ComprehensionLarge-scale SimpleQuestion Answering with…Large-scale Simple Question Answering with Memory NetworksTeaching Machines toRead and ComprehendTeaching Machines to Read and ComprehendAsk Me Anything: DynamicMemory Networks for…Ask Me Anything: Dynamic Memory Networks for Natural Language ProcessingThe GoldilocksPrinciple: Reading…The Goldilocks Principle: Reading Children's Books with Explicit Memory RepresentationsSQuAD: 100, 000+Questions for Machine…SQuAD: 100, 000+ Questions for Machine Comprehension of TextScaling Memory-AugmentedNeural Networks with…Scaling Memory-Augmented Neural Networks with Sparse Reads and WritesCFO: Conditional FocusedNeural Question…CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge BasesMS MARCO: A HumanGenerated MAchine…MS MARCO: A Human Generated MAchine Reading COmprehension Dataset.Reading Comprehensionusing Entity-based…Reading Comprehension using Entity-based Memory NetworkHierarchical MemoryNetworksHierarchical Memory NetworksAddressing a QuestionAnswering Challenge by…Addressing a Question Answering Challenge by Combining Statistical Methods with Inductive Rule Learning and ReasoningA Read-Write MemoryNetwork for Movie Story…A Read-Write Memory Network for Movie Story UnderstandingDialog state tracking, amachine reading approac…Dialog state tracking, a machine reading approach using a memory-enhanced neural networkGuessWhat?! VisualObject Discovery throug…GuessWhat?! Visual Object Discovery through Multi-modal DialogueIntegrating OrderInformation and Event…Integrating Order Information and Event Relation for Script Event PredictionExploringGraph-structured Passag…Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural NetworksTowards AI-CompleteQuestion Answering: A…Towards AI-Complete Question Answering: A Set of Prerequisite Toy TasksEarlier referencesFocus paperCiting papersOlderNewer

Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.