Reasoning over paths in large scale knowledge graphs is an important problem
for many applications. In this paper we discuss a simple approach to
automatically build and rank paths between a source and target entity pair with
learned embeddings using a knowledge base completion model (KBC). We assembled
a knowledge graph by mining the available biomedical scientific literature and
extracted a set of high frequency paths to use for validation. We demonstrate
that our method is able to effectively rank a list of known paths between a
pair of entities and also come up with plausible paths that are not present in
the knowledge graph. For a given entity pair we are able to reconstruct the
highest ranking path 60% of the time within the the top 10 ranked paths and
achieve 49% mean average precision. Our approach is compositional since any KBC
model that can produce vector representations of entities can be used.

本论文探讨了一种简单的方法，使用知识库完成模型（KBC）和学习的嵌入向量，自动构建和排序源实体和目标实体对之间的路径。我们使用获取的生物医学科学文献挖掘了一个知识图，并提取了一组高频路径用于验证。实验结果表明，我们的方法能够有效地排列实体对之间的已知路径，并提出了未在知识图中存在的合理路径。对于给定的实体对，我们能够在排名前 10 的路径中 60% 的时间内重构出排名最高的路径，并达到 49％的平均精度。由于任何能够产生实体向量表示的 KBC 模型都可以使用，因此我们的方法具有组合性

通过知识库补全对路径进行推理

Reasoning Over Paths via Knowledge Base Completion

Most text-based information retrieval (IR) systems index objects by words or
phrases. These discrete systems have been augmented by models that use
embeddings to measure similarity in continuous space. But continuous-space
models are typically used just to re-rank the top candidates. We consider the
problem of end-to-end continuous retrieval, where standard approximate nearest
neighbor (ANN) search replaces the usual discrete inverted index, and rely
entirely on distances between learned embeddings. By training simple models
specifically for retrieval, with an appropriate model architecture, we improve
on a discrete baseline by 8% and 26% (MAP) on two similar-question retrieval
tasks. We also discuss the problem of evaluation for retrieval systems, and
show how to modify existing pairwise similarity datasets for this purpose.

通过培训简单的检索专用模型，并采用合适的模型架构，我们考虑了端到端的连续检索问题，并使用标准的近似最近邻搜索代替通常的离散倒排索引，仅依靠学习嵌入之间的距离。在两个相似问题检索任务上，我们在离散基线上实现了 8％和 26％（MAP）的提升，并讨论了检索系统评估的问题，并展示了如何修改现有的成对相似性数据集以实现此目的。