论文标题
通过多个嵌入式链接与实体表示的命名实体
Named Entity Linking with Entity Representation by Multiple Embeddings
论文作者
论文摘要
我们基于多个嵌入的实体表示，建议了一种简单且实用的方法，用于命名实体链接（NEL）。为了探索这种方法，并回顾了其对参数的依赖性，我们衡量其对名称的绩效，这是一个高度挑战的模棱两可的实体数据集。我们的观察结果表明，创建知识库（KB）实体所需的最小数量对于NEL的表现非常重要。嵌入的数量不太重要，并且可以保持较小，只有10个或更少。我们表明，我们对KB实体的表示形式只能使用KB数据调整，并且调整可以提高NEL性能。我们还比较了从调谐语言模型获得的嵌入的NEL性能，与来自CNN / Daily Mail的公共数据集XSUM的更多统一文本进行调整。我们发现，调整各种新闻提供了更好的嵌入。
We propose a simple and practical method for named entity linking (NEL), based on entity representation by multiple embeddings. To explore this method, and to review its dependency on parameters, we measure its performance on Namesakes, a highly challenging dataset of ambiguously named entities. Our observations suggest that the minimal number of mentions required to create a knowledge base (KB) entity is very important for NEL performance. The number of embeddings is less important and can be kept small, within as few as 10 or less. We show that our representations of KB entities can be adjusted using only KB data, and the adjustment can improve NEL performance. We also compare NEL performance of embeddings obtained from tuning language model on diverse news texts as opposed to tuning on more uniform texts from public datasets XSum, CNN / Daily Mail. We found that tuning on diverse news provides better embeddings.
