Enriching Pre-trained Language Model with Entity Information for Relation Classification
TL
TL;DR
This paper proposes a model that both leverages the pre-trained BERT language model and incorporates information from the target entities to tackle the relation classification task and achieves significant improvement over the state-of-the-art method on the SemEval-2010 task 8 relational dataset.
Abstract
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.
References24 items
1
Semantic Relation Classification via Bidirectional LSTM Networks with Entity-aware Attention using Latent Entity Typing
2
Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector
3
Universal Language Model Fine-tuning for Text Classification
4
Attention is All you Need
5