Ensemble Neural Relation Extraction with Adaptive Boosting
This work addresses noisy data issues in relation extraction for natural language processing applications, representing an incremental improvement through ensemble methods.
The paper tackles the problem of wrong labels and noisy data in relation extraction by proposing an ensemble neural network model that combines LSTMs with attention and adaptive boosting, achieving an 8% improvement in F1-score over state-of-the-art models.
Relation extraction has been widely studied to extract new relational facts from open corpus. Previous relation extraction methods are faced with the problem of wrong labels and noisy data, which substantially decrease the performance of the model. In this paper, we propose an ensemble neural network model - Adaptive Boosting LSTMs with Attention, to more effectively perform relation extraction. Specifically, our model first employs the recursive neural network LSTMs to embed each sentence. Then we import attention into LSTMs by considering that the words in a sentence do not contribute equally to the semantic meaning of the sentence. Next via adaptive boosting, we build strategically several such neural classifiers. By ensembling multiple such LSTM classifiers with adaptive boosting, we could build a more effective and robust joint ensemble neural networks based relation extractor. Experiment results on real dataset demonstrate the superior performance of the proposed model, improving F1-score by about 8% compared to the state-of-the-art models.