Extraction of chemical –protein interactions from the literature using neural networks and narrow instance representation

We report the results of several experiments and show that our best model is competitive with more complex sentence representations or network structures, achieving an F1-score of 0.6306 on the test set. The source code of our work, along with detailed statistics, is publicly available.
Source: Database : The Journal of Biological Databases and Curation - Category: Databases & Libraries Source Type: research