arXiv (Cornell University) · 2015 · 565 citations · 14 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningMemoryDeep LearningMulti-task LearningNatural Language UnderstandingNeural NetworksQuestion AnsweringTransfer LearningDataset CurationDataset DescriptionsNeural Question AnsweringQuestion Answering Systems
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.
14
HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
Feng Niu, Benjamin Recht, Christopher Ré et al. · arXiv (Cornell University) · 2011 · 1.2K citations · Full text
Question Answering with Subgraph Embeddings
Antoine Bordes, Sumit Chopra, Jason Weston · 2014 · 645 citations · Full text
Semantic Parsing via Paraphrasing
Jonathan Berant, Percy Liang · 2014 · 535 citations · Full text