CANDiS: Coupled & Attention-Driven Neural Distant Supervision
This work addresses noise reduction in relation extraction for scalable web-scale tasks, representing an incremental improvement by incorporating previously unexplored inter-instance relationships.
The paper tackled noise in distant supervision for relation extraction by exploiting inter-instance couplings across entity-pairs, proposing CANDiS, an end-to-end neural network with instance-level attention, which outperformed state-of-the-art methods on a standard benchmark dataset.
Distant Supervision for Relation Extraction uses heuristically aligned text data with an existing knowledge base as training data. The unsupervised nature of this technique allows it to scale to web-scale relation extraction tasks, at the expense of noise in the training data. Previous work has explored relationships among instances of the same entity-pair to reduce this noise, but relationships among instances across entity-pairs have not been fully exploited. We explore the use of inter-instance couplings based on verb-phrase and entity type similarities. We propose a novel technique, CANDiS, which casts distant supervision using inter-instance coupling into an end-to-end neural network model. CANDiS incorporates an attention module at the instance-level to model the multi-instance nature of this problem. CANDiS outperforms existing state-of-the-art techniques on a standard benchmark dataset.