Jointly Embedding Relations and Mentions for Knowledge Population
This work addresses relation inference for knowledge base population, offering an incremental advance by combining evidence from both structured and unstructured sources.
The paper tackles the problem of predicting relations between entities by jointly embedding knowledge base triplets and textual mentions, achieving significant improvement in relation extraction on the NELL dataset.
This paper contributes a joint embedding model for predicting relations between a pair of entities in the scenario of relation inference. It differs from most stand-alone approaches which separately operate on either knowledge bases or free texts. The proposed model simultaneously learns low-dimensional vector representations for both triplets in knowledge repositories and the mentions of relations in free texts, so that we can leverage the evidence both resources to make more accurate predictions. We use NELL to evaluate the performance of our approach, compared with cutting-edge methods. Results of extensive experiments show that our model achieves significant improvement on relation extraction.