arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.04641cs.CL
收藏

高阶语义角色标注

High-order Semantic Role Labeling

Department of Computer Science and Engineering, Shanghai Jiao Tong University (SJTU)(上海交通大学计算机科学与工程系(SJTU));National Institute of Information and Communications Technology (NICT)(日本信息与通信技术研究所(NICT))

Zuchao Li, Hai Zhao, Rui Wang, Kevin Parnow

摘要:

语义角色标注主要用于标识谓词、参数及其语义关系。由于建模方法的局限性和谓词预识别条件的限制,以往的研究大多集中在谓词与论元之间的关系以及论元之间的相关性上,而谓词之间的相关性长期以来被忽略。在神经网络时代之前,高阶特征和结构学习在建模这种相关性时非常常见。在本文中,我们介绍了神经语义角色标注模型的高阶图结构,这使得该模型不仅可以显式地考虑孤立的谓词-论元对,但也谓词-论元对之间的相互作用。在CoNLL-2009基准测试的7种语言上的实验结果表明,高阶结构学习技术有利于强性能的SRL模型,并进一步提高了我们的基线,以实现新的最先进的结果。

英文摘要:

Semantic role labeling is primarily used to identify predicates, arguments, and their semantic relationships. Due to the limitations of modeling methods and the conditions of pre-identified predicates, previous work has focused on the relationships between predicates and arguments and the correlations between arguments at most, while the correlations between predicates have been neglected for a long time. High-order features and structure learning were very common in modeling such correlations before the neural network era. In this paper, we introduce a high-order graph structure for the neural semantic role labeling model, which enables the model to explicitly consider not only the isolated predicate-argument pairs but also the interaction between the predicate-argument pairs. Experimental results on 7 languages of the CoNLL-2009 benchmark show that the high-order structural learning techniques are beneficial to the strong performing SRL models and further boost our baseline to achieve new state-of-the-art results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑