Our system is the winner of track 1 of the LM-KBC challenge, based on BERT LM; it achieves 55. 0% F-1 score on the hidden test set of the challenge.
While Wikipedia exists in 287 languages, its content is unevenly distributed among them.
We explore the problem of generating natural language summaries for Semantic Web data.
Our model is based on a Recurrent Neural Network (RNN) that is trained over concatenated sequences of comments, a Convolution Neural Network that is trained over Wikipedia sentences and a formulation that couples the two trained embeddings in a multimodal space.