Enriching Pre-trained Language Model with Entity Information for Relation Classification
This addresses the problem of extracting relations between entities for NLP applications, but it is incremental as it builds on existing BERT methods.
The paper tackled relation classification in NLP by proposing a model that enriches the pre-trained BERT language model with entity information, achieving significant improvement over the state-of-the-art method on the SemEval-2010 task 8 dataset.
Relation classification is an important NLP task to extract relations between entities. The state-of-the-art methods for relation classification are primarily based on Convolutional or Recurrent Neural Networks. Recently, the pre-trained BERT model achieves very successful results in many NLP classification / sequence labeling tasks. Relation classification differs from those tasks in that it relies on information of both the sentence and the two target entities. In this paper, we propose a model that both leverages the pre-trained BERT language model and incorporates information from the target entities to tackle the relation classification task. We locate the target entities and transfer the information through the pre-trained architecture and incorporate the corresponding encoding of the two entities. We achieve significant improvement over the state-of-the-art method on the SemEval-2010 task 8 relational dataset.