Structural block driven - enhanced convolutional neural representation for relation extraction
This addresses relation extraction in NLP by reducing noise from irrelevant sentence parts, offering a lightweight approach for tasks like information extraction.
The paper tackles relation extraction by detecting essential sequential tokens associated with entities through dependency analysis (structural blocks) and encoding them with multi-scale CNNs, achieving new state-of-the-art performance on the KBP37 dataset and comparable results on SemEval2010.
In this paper, we propose a novel lightweight relation extraction approach of structural block driven - convolutional neural learning. Specifically, we detect the essential sequential tokens associated with entities through dependency analysis, named as a structural block, and only encode the block on a block-wise and an inter-block-wise representation, utilizing multi-scale CNNs. This is to 1) eliminate the noisy from irrelevant part of a sentence; meanwhile 2) enhance the relevant block representation with both block-wise and inter-block-wise semantically enriched representation. Our method has the advantage of being independent of long sentence context since we only encode the sequential tokens within a block boundary. Experiments on two datasets i.e., SemEval2010 and KBP37, demonstrate the significant advantages of our method. In particular, we achieve the new state-of-the-art performance on the KBP37 dataset; and comparable performance with the state-of-the-art on the SemEval2010 dataset.