Global Relation Embedding for Relation Extraction
This work addresses noise in relation extraction for natural language processing, offering an incremental improvement over existing models.
The paper tackles the wrong labeling problem in textual relation embedding with distant supervision by using global co-occurrence statistics of relations, resulting in improved precision from 83.9% to 89.3% for top relational facts.
We study the problem of textual relation embedding with distant supervision. To combat the wrong labeling problem of distant supervision, we propose to embed textual relations with global statistics of relations, i.e., the co-occurrence statistics of textual and knowledge base relations collected from the entire corpus. This approach turns out to be more robust to the training noise introduced by distant supervision. On a popular relation extraction dataset, we show that the learned textual relation embedding can be used to augment existing relation extraction models and significantly improve their performance. Most remarkably, for the top 1,000 relational facts discovered by the best existing model, the precision can be improved from 83.9% to 89.3%.