Relation and Fact Type Supervised Knowledge Graph Embedding via Weighted Scores

来源 :第十八届中国计算语言学大会暨中国中文信息学会2019学术年会 | 被引量 : 0次 | 上传用户:jiandande
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
  Knowledge graph embedding aims at learning low-dimensional representations for entities and relations in knowledge graph.Previous knowledge graph embedding methods use just one score to measure the plausibility of a fact,which cant fully utilize the latent semantics of entities and relations.Meanwhile,they ignore the type of relations in knowledge graph and dont use fact type explicitly.We instead propose a model to fuse different scores of a fact and utilize relation and fact type information to supervise the training process.Specifically,scores by inner product of a fact and scores by neural network are fused with different weights to measure the plausibility of a fact.For each fact,besides modeling the plausibility,the model learns to classify different relations and differentiate positive facts from negative ones which can be seen as a muti-task method.Experiments show that our model achieves better link prediction performance than multiple strong baselines on two benchmark datasets WN18 and FB15k.
其他文献
Machine translation has achieved impressive performance with the advances in deep learning and rely on large scale parallel corpora.There have been a large number of attempts to extend these successes
学位
Distant supervision is an effective method to generate large-scale la-beled data for relation extraction without expensive manual annotation,but it inevitably suffers from the wrong labeling problem,w
Exploring linguistic features and characteristics helps better understand natural language.Recently,there have been many studies on the internal relationships of linguistic features,such as collocatio
学位
In the field of Natural Language Processing(NLP)of Mongolian,Named Entity Recognition(NER)has great significance.The traditional model is to use the Conditional Random Field(CRF)and Long-Short Term Mo
In the field of machine translation,parallel corpus serves as the most important prerequisite for learning complex mappings between targeted language pairs.However,in practice,the scale of parallel co
Depression detection is a significant issue for human well-being.Conventional diagnosis of depression requires a face-to-face con-versation with a doctor,which limits the likelihood of the identificat
学位
学位