Relation Extraction as Contextualized Sequence Classification

We show that language model based contextualized knowledge graph completion techniques are an effective method for extracting relations and events from noisy user-generated wetlab protocols.

Improving Automated Group Assignments in an Academic Setting

We demonstrate that, contrary to prior belief, a hill climbing approach using an epsilon-greedy strategy is highly effective for forming effective divisions of individuals into groups based on arbitrary fitness scores, outperforming previous approaches in both efficiency and results.