A Practical Framework for Relation Extraction with Noisy Labels Based on Doubly Transitional Loss
This addresses the issue of noisy labels in relation extraction for NLP practitioners, offering an incremental improvement over existing methods.
The paper tackles the problem of noisy labels in relation extraction, which can degrade performance, by introducing a practical deep learning framework with a doubly transitional loss mechanism. The results show comparable or better performance over state-of-the-art methods on datasets like NYT and SemEval 2018 Task 7.
Either human annotation or rule based automatic labeling is an effective method to augment data for relation extraction. However, the inevitable wrong labeling problem for example by distant supervision may deteriorate the performance of many existing methods. To address this issue, we introduce a practical end-to-end deep learning framework, including a standard feature extractor and a novel noisy classifier with our proposed doubly transitional mechanism. One transition is basically parameterized by a non-linear transformation between hidden layers that implicitly represents the conversion between the true and noisy labels, and it can be readily optimized together with other model parameters. Another is an explicit probability transition matrix that captures the direct conversion between labels but needs to be derived from an EM algorithm. We conduct experiments on the NYT dataset and SemEval 2018 Task 7. The empirical results show comparable or better performance over state-of-the-art methods.