基于条件随机场的多线索中文语义角色标注

Multi-clue Chinese semantic role labeling based on conditional random fields

随着人工智能和中文信息处理技术的产业化发展,自然语言处理相关研究已逐步深入到语义理解层次上,而中文语义角色标注则是语义理解领域的核心技术.针对现有线性标注模型无法满足语义信息技术产业化发展对准确率的需求,提出了采用多层级语言学线索组合的模型优化方法.首先,选取综合标注性能优异的条件随机场基准模型,构建相配套的语义角色标注语料库.然后,在模型中融入词法及句式等多层级语言学线索,实现了对模型的多层次优化.最后,通过对比实验各项标注指标,论证了融入的相关语言学线索可以有效增强线性序列模型的标注性能.

With the industrial development of artificial intelligence and Chinese information processing technology,researches on natural language processing is gradually deepening to the level of semantic understanding,and Chinese Semantic Role Labeling is the core technology in the field of semantic understanding.Aiming at the fact that the existing linear labeling model cannot meet the needs of the industrialization of semantic information technology for labeling accuracy,a multi-level linguistic clue combination model optimization method is proposed.First,a benchmark model of conditional random fields with excellent comprehensive labeling performance is selected to build a matching semantic role labeling corpus.Then,multi-level linguistic clues such as morphology and sentence structure are incorporated into the model to achieve multi-level optimization of the model.Finally,by comparing the various indexing experiments,it is demonstrated that the relevant linguistic cues incorporated can effectively enhance the labeling performance of the linear sequence model..