2019/06/14 by Tao Li, Li, Tao, Vivek Srikumar +1 · 7 citations
Computer Science · Mathematics · #Artificial intelligence #Artificial neural network #Chunking (psychology) #Computer science #Deep neural networks #Explainable Artificial Intelligence (XAI) #Inference #Knowledge graph #Machine learning #Natural Language Processing Techniques #Natural language processing #Task (project management) #Topic Modeling #cs.CL #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1906.06298
published in arXiv (Cornell University) (Cornell University) · Accepted in ACL 2019. Minor fixes in Fig 4; extra citation in related works; Typo fix in constraint N3 and its description
openalex publication_date 2019/06/14 · arxiv created 2020/08/19 · arxiv updated 2020/08/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset. Using world knowledge to inform a model, and yet retain the ability to perform end-to-end training remains an open question. In this paper, we present a novel framework for introducing declarative knowledge to neural network architectures in order to guide training and prediction. Our framework systematically compiles logical statements into computation graphs that augment a neural network without extra learnable parameters or manual redesign. We evaluate our modeling strategy on three tasks: machine comprehension, natural language inference, and text chunking. Our experiments show that knowledge-augmented networks can strongly improve over baselines, especially in low-data regimes.