Abstract Knowledge Graph (KG) provides high-quality structured knowledge for various
downstream knowledge-aware tasks (such as recommendation and intelligent question …

Recommender systems have become an essential tool to help resolve the information
overload problem in recent decades. Traditional recommender systems, however, suffer …

Knowledge graph (KG) embedding is to embed components of a KG including entities and
relations into continuous vector spaces, so as to simplify the manipulation while preserving …

Abstract Representation learning of knowledge graphs aims to encode both entities and
relations into a continuous low-dimensional vector space. Most existing methods only …

Named Entity Disambiguation (NED) refers to the task of resolving multiple named entity
mentions in a document to their correct references in a knowledge base (KB)(eg, Wikipedia) …

The embeddings of entities in a large knowledge base (eg, Wikipedia) are highly beneficial
for solving various natural language tasks that involve real world knowledge. In this paper …

近年来, 随着互联网技术和应用模式的迅猛发展, 引发了互联网数据规模的爆炸式增长,
其中包含大量有价值的知识. 如何组织和表达这些知识, 并对其进行深入计算和分析备受关注 …

Distantly supervised relation extraction employs existing knowledge graphs to automatically
collect training data. While distant supervision is effective to scale relation extraction up to …

Capturing associations for knowledge graphs (KGs) through entity alignment, entity type
inference and other related tasks benefits NLP applications with comprehensive knowledge …

Neural entity linking models are very powerful, but run the risk of overfitting to the domain
they are trained in. For this problem, a “domain” is characterized not just by genre of text but …