Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling
Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling
复制标题
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Shuhei Kurita;Hiroki Ouchi;Kentaro Inui;S. Sekine
中科院分区：
文献类型：
--
作者：
Shuhei Kurita;Hiroki Ouchi;Kentaro Inui;S. Sekine
语义角色标注（SRL）是为语义谓词标注语义论元的任务。语义论元与其谓词有着不同的关系，其中某些语义论元是谓词的必要条件，而另一些语义论元则是谓词的辅助条件。为了考虑这种角色和关系的参数的标签顺序，我们引入迭代参数识别（IAI），它结合了全局解码和迭代识别的语义参数。在实验中，我们首先认识到，随机参数标记顺序的模型优于其他启发式顺序，如传统的从左到右的标记顺序。结合简单的强化学习，该模型自发地学习不同于现有启发式顺序的优化标记顺序。该模型与IAI算法实现了竞争力或优于现有模型的结果在标准基准数据集的跨度为基础的SRL：CoNLL-2005和CoNLL-2012。
Semantic Role Labeling (SRL) is the task of labeling semantic arguments for marked semantic predicates. Semantic arguments and their predicates are related in various distinct manners, of which certain semantic arguments are a necessity while others serve as an auxiliary to their predicates. To consider such roles and relations of the arguments in the labeling order, we introduce iterative argument identification (IAI), which combines global decoding and iterative identification for the semantic arguments. In experiments, we first realize that the model with random argument labeling orders outperforms other heuristic orders such as the conventional left-to-right labeling order. Combined with simple reinforcement learning, the proposed model spontaneously learns the optimized labeling orders that are different from existing heuristic orders. The proposed model with the IAI algorithm achieves competitive or outperforming results from the existing models in the standard benchmark datasets of span-based SRL: CoNLL-2005 and CoNLL-2012.