Lexical Event Ordering with an Edge-Factored Model
Lexical Event Ordering with an Edge-Factored Model
复制标题
使用边缘因子模型进行词汇事件排序
DOI：
10.3115/v1/n15-1122
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Mark Steedman
中科院分区：
文献类型：
--
作者：
Omri Abend;Shay B. Cohen;Mark Steedman
时间分析和规划任务需要广泛的词汇知识。我们在本文中讨论了一种允许直接合并丰富特征和结构约束的词汇设置。我们探索词汇事件排序任务，即仅根据事件的谓词和参数的身份来确定事件可能的时间顺序。我们为任务提出了一种“边缘因子”模型，该模型在事件图的边缘上进行分解。我们使用结构化感知器来学习它。由于词汇任务需要大量文本，因此我们不会尝试手动注释，而是使用事件的文本顺序，该顺序与时间顺序（即烹饪食谱）一致。
Extensive lexical knowledge is necessary for temporal analysis and planning tasks. We address in this paper a lexical setting that allows for the straightforward incorporation of rich features and structural constraints. We explore a lexical event ordering task, namely determining the likely temporal order of events based solely on the identity of their predicates and arguments. We propose an “edgefactored” model for the task that decomposes over the edges of the event graph. We learn it using the structured perceptron. As lexical tasks require large amounts of text, we do not attempt manual annotation and instead use the textual order of events in a domain where this order is aligned with their temporal order, namely cooking recipes.
DOI：
10.1162/tacl_a_00207
发表时间：
2013-03
影响因子：
10.9
作者：
Michaela Regneri;Marcus Rohrbach;Dominikus Wetzel;Stefan Thater;B. Schiele;Manfred Pinkal
通讯作者：
Michaela Regneri;Marcus Rohrbach;Dominikus Wetzel;Stefan Thater;B. Schiele;Manfred Pinkal