We present a novel, language-agnostic approach to "priming" language models for the task of event extraction, providing particularly effective performance in low-resource and zero-shot cross-lingual settings. With priming, we augment the input to the transformer stack's language model differently depending on the question(s) being asked of the model at runtime. For instance, if the model is being asked to identify arguments for the trigger "protested", we will provide that trigger as part of the input to the language model, allowing it to produce different representations for candidate arguments than when it is asked about arguments for the trigger "arrest" elsewhere in the same sentence. We show that by enabling the language model to better compensate for the deficits of sparse and noisy training data, our approach improves both trigger and argument detection and classification significantly over the state of the art in a zero-shot cross-lingual setting.
翻译:我们对事件提取任务的“优先”语言模式提出了一种新颖的、语言不可知性的方法,在低资源和零点截断的跨语言环境中提供特别有效的表现。随着快速增长,我们根据运行时对变压器堆叠语言模式的询问,对变压器堆放语言模式的投入将有所不同。例如,如果要求该模式确定触发“经过验证”的论据,我们将提供触发因素,作为语言模式投入的一部分,允许该模式为候选人的论据提供不同的表述,而不是在同一个句子中询问触发“逮捕”的论据。我们表明,通过使语言模式能够更好地弥补稀少和紧张的培训数据不足,我们的方法将大大改善触发因素和辨别辩论,并在零发式跨语言环境中对艺术状态进行显著分类。