No abstract

Entity alignment aims to link entities and their counterparts among multiple knowledge graphs (KGs). Most existing methods typically rely on external information of entities such as Wikipedia links and require costly manual feature construction to complete alignment. In this paper, we present a novel approach for entity alignment via joint knowledge embeddings. Our method jointly encodes both entities and relations of various KGs into a unified low-dimensional semantic space according to a small seed set of aligned entities. During this process, we can align entities according to their semantic distance in this joint semantic space. More specifically, we present an iterative and parameter sharing method to improve alignment performance. Experiment results on realworld datasets show that, as compared to baselines, our method achieves significant improvements on entity alignment, and can further improve knowledge graph completion performance on various KGs with the favor of joint knowledge embeddings.

Representation learning (RL) of knowledge graphs aims to project both entities and relations into a continuous low-dimensional space. Most methods concentrate on learning representations with knowledge triples indicating relations between entities. In fact, in most knowledge graphs there are usually concise descriptions for entities, which cannot be well utilized by existing methods. In this paper, we propose a novel RL method for knowledge graphs taking advantages of entity descriptions. More specifically, we explore two encoders, including continuous bag-of-words and deep convolutional neural models to encode semantics of entity descriptions. We further learn knowledge representations with both triples and descriptions. We evaluate our method on two tasks, including knowledge graph completion and entity classification. Experimental results on real-world datasets show that, our method outperforms other baselines on the two tasks, especially under the zero-shot setting, which indicates that our method is capable of building representations for novel entities according to their descriptions. The source code of this paper can be obtained from https://github.com/xrb92/DKRL.

No abstract

This paper revisits the debate on the role of agriculture in promoting economic growth in a selection of nine developing countries. We investigated the causal linkages between agriculture and gross domestic product growth with the aid of directed acyclic graphs, a recently developed algorithm of inductive causation. The results suggest that while agriculture could be an engine of economic growth, the impact varies across countries. In some cases, we found strong evidence in support of the agricultureled growth hypothesis. In contrast, the results for some other countries indicate that having a vibrant aggregate economy is a prerequisite for agricultural development.Le présent article réexamine le débat sur le rôle de l'agriculture dans la promotion de la croissancé economique de neuf pays en développement. Nous avonsétudié les liens de causalité entre l'agriculture et la croissance du PIBà l'aide de graphes acycliques orientés, un algorithme de causalité inductive récemment mis au point. Les résultats montrent que, même si l'agriculture peut constituer un engin de croissanceéconomique, son impact varie d'un paysà l'autre. Dans certains cas, nous avons obtenu des preuves solides qui appuient l'hypothèse selon laquelle la croissance est motivée par l'agriculture. En revanche, les résultats obtenus dans le cas d'autres pays indiquent qu'uneéconomie globale vigoureuse constitue une condition préalable au développement de l'agriculture.