Attending to All Mention Pairs for Full Abstract Biological Relation Extraction
This addresses the challenge of extracting complex biological relations from text for biomedical researchers, though it is an incremental improvement over existing methods.
The paper tackles the problem of biological relation extraction where relations are expressed across sentences or require large context, by proposing a model that considers all mention and entity pairs simultaneously in full paper abstracts. The result is state-of-the-art performance on the Biocreative V Chemical Disease Relation dataset for models without KB resources, outperforming ensembles using hand-crafted features and additional linguistic resources.
Most work in relation extraction forms a prediction by looking at a short span of text within a single sentence containing a single entity pair mention. However, many relation types, particularly in biomedical text, are expressed across sentences or require a large context to disambiguate. We propose a model to consider all mention and entity pairs simultaneously in order to make a prediction. We encode full paper abstracts using an efficient self-attention encoder and form pairwise predictions between all mentions with a bi-affine operation. An entity-pair wise pooling aggregates mention pair scores to make a final prediction while alleviating training noise by performing within document multi-instance learning. We improve our model's performance by jointly training the model to predict named entities and adding an additional corpus of weakly labeled data. We demonstrate our model's effectiveness by achieving the state of the art on the Biocreative V Chemical Disease Relation dataset for models without KB resources, outperforming ensembles of models which use hand-crafted features and additional linguistic resources.