arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.07352cs.IRcs.CLcs.LGcs.SI
收藏

MOLEMAN:实体与提及注释网络的仅提及链接

MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network

Google Research(谷歌研究院)

Nicholas FitzGerald, Jan A. Botha, Daniel Gillick, Daniel M. Bikel, Tom Kwiatkowski, Andrew McCallum

摘要:

我们提出了一个基于实例的最近邻实体链接方法。与大多数先前的实体检索系统,表示每个实体与一个单一的向量相比,我们建立了一个上下文提到编码器,学习放置类似的提到同一实体更接近的向量空间比提到不同的实体。这种方法允许实体的所有提及充当“类原型”,因为推理涉及从训练集中的标记实体提及的全集中检索并应用最近提及邻居的实体标签。我们的模型在来自维基百科超链接的提及对的大型多语言语料库上进行训练,并对7亿次提及的索引进行最近邻推理。它更容易训练,给出更多可解释的预测,并在两个多语言实体链接基准上优于所有其他系统。

英文摘要:

We present an instance-based nearest neighbor approach to entity linking. In contrast to most prior entity retrieval systems which represent each entity with a single vector, we build a contextualized mention-encoder that learns to place similar mentions of the same entity closer in vector space than mentions of different entities. This approach allows all mentions of an entity to serve as "class prototypes" as inference involves retrieving from the full set of labeled entity mentions in the training set and applying the nearest mention neighbor's entity label. Our model is trained on a large multilingual corpus of mention pairs derived from Wikipedia hyperlinks, and performs nearest neighbor inference on an index of 700 million mentions. It is simpler to train, gives more interpretable predictions, and outperforms all other systems on two multilingual entity linking benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑