2017/03/13 by Georgiana Dinu, Dinu, Georgiana, Wael Hamza +3
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.1703.04489
Deep Reinforcement Learning Workshop, NIPS 2016
arxiv created 2017/03/13 · arxiv updated 2017/03/14
This paper describes an application of reinforcement learning to the mention detection task. We define a novel action-based formulation for the mention detection task, in which a model can flexibly revise past labeling decisions by grouping together tokens and assigning partial mention labels. We devise a method to create mention-level episodes and we train a model by rewarding correctly labeled complete mentions, irrespective of the inner structure created. The model yields results which are on par with a competitive supervised counterpart while being more flexible in terms of achieving targeted behavior through reward modeling and generating internal mention structure, especially on longer mentions.