论文标题
XLTime：时间表达式提取的跨语性知识转移框架
XLTime: A Cross-Lingual Knowledge Transfer Framework for Temporal Expression Extraction
论文作者
论文摘要
时间表达提取（TEE）对于理解自然语言的时间至关重要。它具有自然语言处理（NLP）任务的应用，例如问题回答，信息检索和因果推断。迄今为止，该领域的工作主要集中在英语上，因为其他语言的标记数据稀缺。我们提出了XLTime，这是一个多语言T恤的新型框架。 XLTime在预先训练的语言模型之上工作，并利用多任务学习，以促使英语和非英语语言中的跨语言知识转移。 XLTime减轻了由于目标语言缺少数据而引起的问题。我们将XLTime应用于不同的语言模型，并表明它的表现优于先前的法语，西班牙语，葡萄牙语和巴斯克语的自动SOTA方法。 XLTime还可以在手工制作的海德期权方法上大大缩小差距。
Temporal Expression Extraction (TEE) is essential for understanding time in natural language. It has applications in Natural Language Processing (NLP) tasks such as question answering, information retrieval, and causal inference. To date, work in this area has mostly focused on English as there is a scarcity of labeled data for other languages. We propose XLTime, a novel framework for multilingual TEE. XLTime works on top of pre-trained language models and leverages multi-task learning to prompt cross-language knowledge transfer both from English and within the non-English languages. XLTime alleviates problems caused by a shortage of data in the target language. We apply XLTime with different language models and show that it outperforms the previous automatic SOTA methods on French, Spanish, Portuguese, and Basque, by large margins. XLTime also closes the gap considerably on the handcrafted HeidelTime method.
