Sang-hyun Je

Sang-Hyun Je

Knowledge graph (KG) embedding is widely used in many downstream applications using KGs. Generally, since KGs contain only ground truth triples, it is necessary to construct arbitrary negative samples for representation learning of KGs. Recently, various methods for sampling high-quality negatives have been studied because the quality of negative triples has great effect on KG embedding. In this paper, we propose a novel method called Entity Aware Negative Sampling (EANS), which is able to sample negative entities resemble to positive one by adopting Gaussian distribution to the aligned entity index space. Additionally, we introduce auxiliary loss for false negative prediction that can alleviate the impact of the sampled false negative triples. The proposed method can generate high-quality negative samples regardless of negative sample size and effectively mitigate the influence of false negative samples. The experimental results on standard benchmarks show that our EANS outperforms existing the state-of-the-art methods of negative sampling on several knowledge graph embedding models. Moreover, the proposed method achieves competitive performance even when the number of negative samples is limited to only one.

Sang-Hyun Je, Wontae Choi, Kwangjin Oh

The goal of knowledge graph completion (KGC) is to predict missing links in a KG using trained facts that are already known. In recent, pre-trained language model (PLM) based methods that utilize both textual and structural information are emerging, but their performances lag behind state-of-the-art (SOTA) structure-based methods or some methods lose their inductive inference capabilities in the process of fusing structure embedding to text encoder. In this paper, we propose a novel method to effectively unify structure information and language semantics without losing the power of inductive reasoning. We adopt entity anchors and these anchors and textual description of KG elements are fed together into the PLM-based encoder to learn unified representations. In addition, the proposed method utilizes additional random negative samples which can be reused in the each mini-batch during contrastive learning to learn a generalized entity representations. We verify the effectiveness of the our proposed method through various experiments and analysis. The experimental results on standard benchmark widely used in link prediction task show that the proposed model outperforms existing the SOTA KGC models. Especially, our method show the largest performance improvement on FB15K-237, which is competitive to the SOTA of structure-based KGC methods.

Minsang Kim, Sang-hyun Je, Eunjoo Park

In recent years, creating and managing knowledge bases have become crucial to the retail product and enterprise domains. We present an automatic knowledge base construction system that mines data from documents. This system can generate training data during the training process without human intervention. Therefore, it is domain-agnostic trainable using only the target domain text corpus and a pre-defined knowledge base. This system is called OASYS and is the first system built with the Korean language in mind. In addition, we also have constructed a new human-annotated benchmark dataset of the Korean Wikipedia corpus paired with a Korean DBpedia to aid system evaluation. The system performance results on human-annotated benchmark test dataset are meaningful and show that the generated knowledge base from OASYS trained on only auto-generated data is useful. We provide both a human-annotated test dataset and an auto-generated dataset.