Semantic Relation Classification via Bidirectional LSTM Networks with Entity-aware Attention using Latent Entity Typing
This addresses the problem of accurately classifying semantic relations in NLP, which is important for tasks like information extraction, but is incremental as it builds on existing neural attention models.
The paper tackles semantic relation classification between entity pairs in sentences by proposing a bidirectional LSTM network with entity-aware attention and latent entity typing, achieving state-of-the-art performance on the SemEval-2010 Task 8 benchmark without using high-level lexical or syntactic features.
Classifying semantic relations between entity pairs in sentences is an important task in Natural Language Processing (NLP). Most previous models for relation classification rely on the high-level lexical and syntactic features obtained by NLP tools such as WordNet, dependency parser, part-of-speech (POS) tagger, and named entity recognizers (NER). In addition, state-of-the-art neural models based on attention mechanisms do not fully utilize information of entity that may be the most crucial features for relation classification. To address these issues, we propose a novel end-to-end recurrent neural model which incorporates an entity-aware attention mechanism with a latent entity typing (LET) method. Our model not only utilizes entities and their latent types as features effectively but also is more interpretable by visualizing attention mechanisms applied to our model and results of LET. Experimental results on the SemEval-2010 Task 8, one of the most popular relation classification task, demonstrate that our model outperforms existing state-of-the-art models without any high-level features.