Context-aware Frame-Semantic Role Labeling
Context-aware Frame-Semantic Role Labeling
复制标题
DOI：
10.1162/tacl_a_00150
复制
发表时间：
2015-08
影响因子：
10.9
通讯作者：
Michael Roth;Mirella Lapata
中科院分区：
文献类型：
--
作者：
Michael Roth;Mirella Lapata
框架语义表示在从文本到场景生成、到问题回答和社会网络分析的多个应用中都很有用。然而，从原始文本预测这样的表示是一项具有挑战性的任务，相应的模型通常只在一小部分句子级注释上进行训练。本文提出了一种考虑句子和语篇语境的语义角色标注系统。我们引入了几个基于语言学洞察的新功能，并通过实验证明，它们在基于FrameNet的语义角色标注方面比目前最先进的水平有了显着的改进。
Frame semantic representations have been useful in several applications ranging from text-to-scene generation, to question answering and social network analysis. Predicting such representations from raw text is, however, a challenging task and corresponding models are typically only trained on a small set of sentence-level annotations. In this paper, we present a semantic role labeling system that takes into account sentence and discourse context. We introduce several new features which we motivate based on linguistic insights and experimentally demonstrate that they lead to significant improvements over the current state-of-the-art in FrameNet-based semantic role labeling.