A Bi-LSTM-RNN Model for Relation Classification Using Low-Cost Sequence Features
This work addresses the inconvenience and domain-dependency of structural features in relation classification for AI applications, though it is incremental as it adapts existing neural methods to a new feature type.
The paper tackles relation classification by proposing a Bi-LSTM-RNN model using low-cost sequence features instead of high-cost structural features, achieving comparable performance on SemEval-2010 Task 8 and third-best results on BioNLP-ST 2016 Task BB3.
Relation classification is associated with many potential applications in the artificial intelligence area. Recent approaches usually leverage neural networks based on structure features such as syntactic or dependency features to solve this problem. However, high-cost structure features make such approaches inconvenient to be directly used. In addition, structure features are probably domain-dependent. Therefore, this paper proposes a bi-directional long-short-term-memory recurrent-neural-network (Bi-LSTM-RNN) model based on low-cost sequence features to address relation classification. This model divides a sentence or text segment into five parts, namely two target entities and their three contexts. It learns the representations of entities and their contexts, and uses them to classify relations. We evaluate our model on two standard benchmark datasets in different domains, namely SemEval-2010 Task 8 and BioNLP-ST 2016 Task BB3. In the former dataset, our model achieves comparable performance compared with other models using sequence features. In the latter dataset, our model obtains the third best results compared with other models in the official evaluation. Moreover, we find that the context between two target entities plays the most important role in relation classification. Furthermore, statistic experiments show that the context between two target entities can be used as an approximate replacement of the shortest dependency path when dependency parsing is not used.