Antecedent Prediction Without a Pipeline

摘要

We consider several antecedent prediction models that use no pipelined features generated by upstream systems. Models trained in this way are interesting because they allow for side-stepping the intricacies of upstream models, and because we might expect them to generalize better to situations in which upstream features are unavailable or unreliable. Through quantitative and qualitative error analysis we identify what sorts of cases are particularly difficult for such models, and suggest some directions for further improvement.