论文标题
MAPS-KB：一百万尺度的概率明喻知识库
MAPS-KB: A Million-scale Probabilistic Simile Knowledge Base
论文作者
论文摘要
理解和生成明喻的能力是实现人级AI的当务之急。但是，机器智能和比喻中的人类认知之间仍然存在很大的差距，因为基于统计分布的深层模型倾向于有利于高频喻。因此，需要大规模的比喻符号知识基础，因为它有助于对各种但不受欢迎的明喻进行建模，同时促进其他评估和推理。为了弥合差距，我们提出了一个新颖的框架，用于大规模明喻知识库结构，以及两个概率指标，可以提高对自然语言中明喻现象的了解。总体而言，我们构建了MAPS-KB，这是一百万个概率的明喻知识库，涵盖了70 GB Corpora的430万个三胞胎。我们进行了足够的实验，以证明我们框架方法的有效性和必要性是合理的。我们还将MAPS-KB应用于三个下游任务以实现最新性能，进一步证明了MAPS-KB的价值。
The ability to understand and generate similes is an imperative step to realize human-level AI. However, there is still a considerable gap between machine intelligence and human cognition in similes, since deep models based on statistical distribution tend to favour high-frequency similes. Hence, a large-scale symbolic knowledge base of similes is required, as it contributes to the modeling of diverse yet unpopular similes while facilitating additional evaluation and reasoning. To bridge the gap, we propose a novel framework for large-scale simile knowledge base construction, as well as two probabilistic metrics which enable an improved understanding of simile phenomena in natural language. Overall, we construct MAPS-KB, a million-scale probabilistic simile knowledge base, covering 4.3 million triplets over 0.4 million terms from 70 GB corpora. We conduct sufficient experiments to justify the effectiveness and necessity of the methods of our framework. We also apply MAPS-KB on three downstream tasks to achieve state-of-the-art performance, further demonstrating the value of MAPS-KB.
