Word-Label Alignment for Event Detection: A New Perspective via Optimal Transport
Word-Label Alignment for Event Detection: A New Perspective via Optimal Transport
复制标题
DOI：
10.18653/v1/2022.starsem-1.11
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Amir Pouran Ben Veyseh;Thien Huu Nguyen
中科院分区：
文献类型：
--
作者：
Amir Pouran Ben Veyseh;Thien Huu Nguyen
事件检测（ED）旨在识别文本中现实世界事件的提及/触发。在文献中，该任务被建模为序列标记或单词预测问题。在这项工作中，我们提出了一种新颖的公式，其中 ED 被建模为单词标签对齐任务。特别是，给定句子中的单词和可能的事件类型，目标是推断一个对齐矩阵，其中事件触发词与最可能的事件类型对齐。此外，我们表明，这种新视角有助于结合单词标签对齐偏差来改进 ED 的对齐矩阵。引入新颖的对齐偏差和最佳传输来解决 ED 的对齐问题。我们在基准数据集上进行实验，以证明所提出的 ED 模型的有效性。
Event Detection (ED) aims to identify mentions/triggers of real world events in text. In the literature, this task is modeled as a sequence-labeling or word-prediction problem. In this work, we present a novel formulation in which ED is modeled as a word-label alignment task. In particular, given the words in a sentence and possible event types, the objective is to infer an alignment matrix in which event trigger words are aligned with the most likely event types. Moreover, we show that this new perspective facilitates the incorporation of word-label alignment biases to improve alignment matrix for ED. Novel alignment biases and Optimal Transport are introduced to solve our alignment problem for ED. We conduct experiments on a benchmark dataset to demonstrate the effectiveness of the proposed model for ED.