2019 · 36 citations · 24 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingDeep LearningInformation ExtractionLanguage ModelingRelation ExtractionSupervised LearningUnsupervised LearningLoss Distribution ApproachLoss Distribution EstimationLoss Distribution TheoryRelation PredictionUnsupervised Information Extraction
Unsupervised relation extraction aims at extracting relations between entities in text. Previous unsupervised approaches are either generative or discriminative. In a supervised setting, discriminative approaches, such as deep neural network classifiers, have demonstrated substantial improvement. However, these models are hard to train without supervision, and the currently proposed solutions are unstable. To overcome this limitation, we introduce a skewness loss which encourages the classifier to predict a relation with confidence given a sentence, and a distribution distance loss enforcing that all relations are predicted in average. These losses improve the performance of discriminative based models, and enable us to train deep neural networks satisfactorily, surpassing current state of the art on three different datasets.
24
Distributed Representations of Words and Phrases and their Compositionality
Tomáš Mikolov, Ilya Sutskever, Kai Chen et al. · arXiv (Cornell University) · 2013 · 18.1K citations · Full text
Kurt Bollacker, Colin Evans, Praveen Paritosh et al. · 2008 · 5K citations
Distant supervision for relation extraction without labeled data
Mike D. Mintz, Steven Bills, Rion Snow et al. · 2009 · 2.9K citations · Full text