Learn More
Knowledge graph completion aims to perform link prediction between entities. In this paper, we consider the approach of knowledge graph embeddings. Recently, models such as TransE and TransH build entity and relation embeddings by regarding a relation as translation from head entity to tail entity. We note that these models simply put both entities and(More)
Representation learning of knowledge bases (KBs) aims to embed both entities and relations into a low-dimensional space. Most existing methods only consider direct relations in representation learning. We argue that multiple-step relation paths also contain rich inference patterns between entities, and propose a pathbased representation learning model. This(More)
Distant supervised relation extraction has been widely used to find novel relational facts from text. However, distant supervision inevitably accompanies with the wrong labelling problem, and these noisy data will substantially hurt the performance of relation extraction. To alleviate this issue, we propose a sentence-level attention-based model for(More)
Document-level sentiment classification aims to predict user’s overall sentiment in a document about a product. However, most of existing methods only focus on local text information and ignore the global user preference and product characteristics. Even though some works take such information into account, they usually suffer from high model complexity and(More)
Distributed knowledge representation (KR) encodes both entities and relations in a lowdimensional semantic space, which has significantly promoted the performance of relation extraction and knowledge reasoning. In many knowledge graphs (KG), some relations indicate attributes of entities (attributes) and others indicate relations between entities(More)
Distantly supervised relation extraction has been widely used to find novel relational facts from plain text. To predict the relation between a pair of two target entities, existing methods solely rely on those direct sentences containing both entities. In fact, there are also many sentences containing only one of the target entities, which also provide(More)
Recently, neural models have been proposed for headline generation by learning to map documents to headlines with recurrent neural network. In this work, we give a detailed introduction and comparison of existing work and recent improvements in neural headline generation, with particular attention on how encoders, decoders and neural model training(More)
The human brain as one of the most complex dynamic systems enables us to communicate and externalise information by natural language. Despite extensive research, human-like communication with interactive robots is not yet possible, because we have not yet fully understood the mechanistic characteristics of the crossmodal binding between language, actions,(More)
  • 1