论文标题
位置转喻分辨率的目标单词掩蔽
Target Word Masking for Location Metonymy Resolution
论文作者
论文摘要
现有的转换分辨率方法依赖于从词典和手工制作的词汇资源等外部资源中提取的功能。在本文中，我们仅基于伯特（Bert）提出了一种端到端的单词级分类方法，而没有对标签者，解析器，位置名称的策划字典或其他外部资源的依赖。我们表明，我们的方法实现了5个数据集的最新方法，从而超过了传统的BERT模型和基准。我们还表明，我们的方法对看不见的数据有很好的概括。
Existing metonymy resolution approaches rely on features extracted from external resources like dictionaries and hand-crafted lexical resources. In this paper, we propose an end-to-end word-level classification approach based only on BERT, without dependencies on taggers, parsers, curated dictionaries of place names, or other external resources. We show that our approach achieves the state-of-the-art on 5 datasets, surpassing conventional BERT models and benchmarks by a large margin. We also show that our approach generalises well to unseen data.
