Recommender systems have become an essential tool to help resolve the information overload problem in recent decades. Traditional recommender systems, however, suffer …
Q Wang, Z Mao, B Wang, L Guo - IEEE transactions on …, 2017 - ieeexplore.ieee.org
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 …
R Xie, Z Liu, M Sun - IJCAI, 2016 - nlp.csai.tsinghua.edu.cn
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 …
Distantly supervised relation extraction employs existing knowledge graphs to automatically collect training data. While distant supervision is effective to scale relation extraction up to …
Z Sun, M Chen, W Hu, C Wang, J Dai… - arXiv preprint arXiv …, 2020 - arxiv.org
Capturing associations for knowledge graphs (KGs) through entity alignment, entity type inference and other related tasks benefits NLP applications with comprehensive knowledge …
Y Onoe, G Durrett - Proceedings of the AAAI Conference on Artificial …, 2020 - ojs.aaai.org
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 …