Abstract | ||
---|---|---|
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. |
Year | Venue | Field |
---|---|---|
2017 | arXiv: Computation and Language | Computer science,Artificial intelligence,Machine learning,Reinforcement learning |
DocType | Volume | Citations |
Journal | abs/1703.04489 | 0 |
PageRank | References | Authors |
0.34 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Georgiana Dinu | 1 | 510 | 33.36 |
wael hamza | 2 | 198 | 15.84 |
Radu Florian | 3 | 924 | 91.44 |