news event element extract aims to extract the event arguments that describe the topic event in the news text,such as time,location,people,and organization.To perform the event element extraction on low-resource lan-guages,this paper proposes a Chinese-Vietnamese Cross-language News Event Element extraction via machine read-ing comprehension.First,we apply the key sentence retrieval from the long news text to filter noisy sentences.Then we use the cross-language machine reading comprehension model to transfer rich resource language knowledge to improve the performance of Vietnamese news event element extraction.Experiments on the self-built Chinese-Viet-namese bilingual data set prove the effectiveness of this method.
关键词
新闻事件要素抽取/长文本语义建模/跨语言知识迁移/阅读理解
Key words
news event element extraction/long text sematic modeling/cross-language knowledge transfer/reading comprehension
维普
万方数据