Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction
This addresses the need for better updating of knowledge bases from text, though it appears incremental in unifying existing methods.
The paper tackles the problem of unifying relation extraction (RE) and knowledge base embeddings (KBE) to improve RE, achieving significant state-of-the-art improvements.
Knowledge Bases (KBs) require constant up-dating to reflect changes to the world they represent. For general purpose KBs, this is often done through Relation Extraction (RE), the task of predicting KB relations expressed in text mentioning entities known to the KB. One way to improve RE is to use KB Embeddings (KBE) for link prediction. However, despite clear connections between RE and KBE, little has been done toward properly unifying these models systematically. We help close the gap with a framework that unifies the learning of RE and KBE models leading to significant improvements over the state-of-the-art in RE. The code is available at https://github.com/billy-inn/HRERE.