Hybrid Knowledge Transfer for Improved Cross-Lingual Event Detection via Hierarchical Sample Selection
Hybrid Knowledge Transfer for Improved Cross-Lingual Event Detection via Hierarchical Sample Selection
复制标题
DOI：
10.18653/v1/2023.acl-long.296
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Luis Guzman Nateras;Franck Dernoncourt;Thien Huu Nguyen
中科院分区：
文献类型：
--
作者：
Luis Guzman Nateras;Franck Dernoncourt;Thien Huu Nguyen
在本文中，我们解决了零镜头跨语言设置下的事件检测任务，其中模型在源语言上训练，但在没有标记数据的不同目标语言上进行评估。最近在这一领域的努力遵循直接迁移方法，其中使用语言不变特征训练模型，然后直接应用于目标语言。然而，我们认为，这些方法未能利用数据传输方法的优势，其中跨语言模型是在目标语言数据上训练的，并且能够从目标语言的句法特征或词标签关系中学习特定于任务的信息。因此，我们提出了一种混合的知识转移方法，利用教师和学生的网络分别按照直接和数据传输方法进行训练的教师-学生框架。我们的方法是由一个分层的训练样本选择方案，旨在解决由教师模型产生的噪声标签的问题。我们的模型在3个不同数据集的9种形态多样的目标语言上取得了最先进的结果，突出了利用混合迁移优势的重要性。
In this paper, we address the Event Detection task under a zero-shot cross-lingual setting where a model is trained on a source language but evaluated on a distinct target language for which there is no labeled data available. Most recent efforts in this field follow a direct transfer approach in which the model is trained using language-invariant features and then directly applied to the target language. However, we argue that these methods fail to take advantage of the benefits of the data transfer approach where a cross-lingual model is trained on target-language data and is able to learn task-specific information from syntactical features or word-label relations in the target language. As such, we propose a hybrid knowledge-transfer approach that leverages a teacher-student framework where the teacher and student networks are trained following the direct and data transfer approaches, respectively. Our method is complemented by a hierarchical training-sample selection scheme designed to address the issue of noisy labels being generated by the teacher model. Our model achieves state-of-the-art results on 9 morphologically-diverse target languages across 3 distinct datasets, highlighting the importance of exploiting the benefits of hybrid transfer.