Vancouver Welcomes You! Minimalist Location Metonymy Resolution
Vancouver Welcomes You! Minimalist Location Metonymy Resolution
复制标题
DOI：
10.18653/v1/p17-1115
复制
发表时间：
2017-08
期刊：
影响因子：
--
通讯作者：
Milan Gritta;Mohammad Taher Pilehvar;Nut Limsopatham;Nigel Collier
中科院分区：
文献类型：
--
作者：
Milan Gritta;Mohammad Taher Pilehvar;Nut Limsopatham;Nigel Collier
命名实体经常以一种换喻的方式使用。它们作为相关实体的参考，如个人和组织。转喻的准确识别和解释可以直接有益于各种自然语言处理应用，例如命名实体识别和地理分析。到目前为止，转喻消解方法主要依赖于语法分析器、标注器、词典、外部词表和其他手工制作的词汇资源。我们展示了如何最低限度的神经方法结合一种新的谓词窗口方法可以实现有竞争力的结果SemEval 2007年的任务上的转喻决议。此外，我们还贡献了一个新的基于维基百科的MR数据集，称为RelocaR，它是针对位置定制的，并改善了以前注释指南中的缺陷。
Named entities are frequently used in a metonymic manner. They serve as references to related entities such as people and organisations. Accurate identification and interpretation of metonymy can be directly beneficial to various NLP applications, such as Named Entity Recognition and Geographical Parsing. Until now, metonymy resolution (MR) methods mainly relied on parsers, taggers, dictionaries, external word lists and other handcrafted lexical resources. We show how a minimalist neural approach combined with a novel predicate window method can achieve competitive results on the SemEval 2007 task on Metonymy Resolution. Additionally, we contribute with a new Wikipedia-based MR dataset called RelocaR, which is tailored towards locations as well as improving previous deficiencies in annotation guidelines.