No abstract

With the explosive growth of artificial intelligence (AI) and big data, it has become vitally important to organize and represent the enormous volume of knowledge appropriately. As graph data, knowledge graphs accumulate and convey knowledge of the real world. It has been well-recognized that knowledge graphs effectively represent complex information; hence, they rapidly gain the attention of academia and industry in recent years. Thus to develop a deeper understanding of knowledge graphs, this paper presents a systematic overview of this field. Specifically, we focus on the opportunities and challenges of knowledge graphs. We first review the opportunities of knowledge graphs in terms of two aspects: (1) AI systems built upon knowledge graphs; (2) potential application fields of knowledge graphs. Then, we thoroughly discuss severe technical challenges in this field, such as knowledge graph embeddings, knowledge acquisition, knowledge graph completion, knowledge fusion, and knowledge reasoning. We expect that this survey will shed new light on future research and the development of knowledge graphs.

Relations in knowledge graphs have rich relational structures and various binary relational patterns. Various relation modelling strategies are proposed for embedding knowledge graphs, but they fail to fully capture both features of relations, rich relational structures and various binary relational patterns. To address the problem of insufficient embedding due to the complexity of the relations, we propose a novel knowledge graph representation model in complex space, namely MARS, to exploit complex relations to embed knowledge graphs. MARS takes the mechanisms of complex numbers and message-passing and then embeds triplets into relation-specific complex hyperplanes. Thus, MARS can well preserve various relation patterns, as well as structural information in knowledge graphs. In addition, we find that the scores generated from the score function approximate a Gaussian distribution. The scores in the tail cannot effectively represent triplets. To address this particular issue and improve the precision of embeddings, we use the standard deviation to limit the dispersion of the score distribution, resulting in more accurate embeddings of triplets. Comprehensive experiments on multiple benchmarks demonstrate that our model significantly outperforms existing state-of-the-art models for link prediction and triple classification.

Recently, with an increasing number of metaphor studies being conducted, research on metaphor interpretation has set off an upsurge. Although a multitude of studies on the interpretation of metaphors exists, many are limited to the understanding of literal meanings without attempting an interpretation of hidden emotions in metaphorical expressions. There are particularly few studies on metaphorical emotions interpretation in literary studies with rich and implicit emotions, such as classical Chinese poetry. This study proposes the interpretation of the metaphorical emotions of special objects in Chinese poetry based on emotion distribution. We present a statistical approach to calculate the emotion distribution of our target objects by exploiting contextual emotion mining. According to the emotion distribution, the emotion with the highest probability is considered the metaphorical emotion of the target object. Subsequently, the metaphorical emotion can be determined as a positive or negative sentiment based on expert annotations. Using the proposed method, we have tested two representative objects, ‘月’ (moon) and ‘风’ (wind), and the accuracy performances were 84% and 83.33%, respectively, for sentiment detection and 66% and 70% for emotion-specific metaphorical interpretation. The results demonstrate that our approach can be used to assist readers with metaphorical emotional understanding in Chinese poetry.

Metaphor is widely used in human communication. The cohort of scholars studying metaphor in various fields is continuously growing, but very few work has been done in bibliographical analysis of metaphor research. This paper examines the advancements in metaphor research from 2000 to 2017. Using data retrieved from Microsoft Academic Graph and Web of Science, this paper makes a macro analysis of metaphor research, and expounds the underlying patterns of its development. Taking into consideration sub-fields of metaphor research, the internal analysis of metaphor research is carried out from a micro perspective to reveal the evolution of research topics and the inherent relationships among them. This paper provides novel insights into the current state of the art of metaphor research as well as future trends in this field, which may spark new research interests in metaphor from both linguistic and interdisciplinary perspectives.