Unsupervised Open Relation Extraction

We explore methods to extract relations between named entities from free text in an unsupervised setting. In addition to standard feature extraction, we develop a novel method to re-weight word embeddings. We alleviate the problem of features sparsity using an individual feature reduction. Our approach exhibits a significant improvement by 5.8% over the state-of-the-art relation clustering scoring a F1-score of 0.416 on the NYT-FB dataset.

Hady Elsahar, Elena Demidova, Simon Gottschalk, Christophe Gravier, Frederique Laforest · 2018