Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix
This addresses noise issues in relation extraction for NLP applications, but it is incremental as it builds on existing distant supervision methods.
The paper tackles noise in distantly supervised relation extraction by using a dynamic transition matrix to characterize noise, and shows consistent improvements and state-of-the-art performance across various scenarios.
Distant supervision significantly reduces human efforts in building training data for many classification tasks. While promising, this technique often introduces noise to the generated training data, which can severely affect the model performance. In this paper, we take a deep look at the application of distant supervision in relation extraction. We show that the dynamic transition matrix can effectively characterize the noise in the training data built by distant supervision. The transition matrix can be effectively trained using a novel curriculum learning based method without any direct supervision about the noise. We thoroughly evaluate our approach under a wide range of extraction scenarios. Experimental results show that our approach consistently improves the extraction results and outperforms the state-of-the-art in various evaluation scenarios.