Compositional Vector Space Models for Knowledge Base Completion

04/24/2015
by   Arvind Neelakantan, et al.
0

Knowledge base (KB) completion adds new facts to a KB by making inferences from existing facts, for example by inferring with high likelihood nationality(X,Y) from bornIn(X,Y). Most previous methods infer simple one-hop relational synonyms like this, or use as evidence a multi-hop relational path treated as an atomic feature, like bornIn(X,Z) -> containedIn(Z,Y). This paper presents an approach that reasons about conjunctions of multi-hop relations non-atomically, composing the implications of a path using a recursive neural network (RNN) that takes as inputs vector embeddings of the binary relation in the path. Not only does this allow us to generalize to paths unseen at training time, but also, with a single high-capacity RNN, to predict new relation types not seen when the compositional model was trained (zero-shot learning). We assemble a new dataset of over 52M relational triples, and show that our method improves over a traditional classifier by 11 pre-trained embeddings by 7

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/06/2016

Improved Knowledge Base Completion by Path-Augmented TransR Model

Knowledge base completion aims to infer new relations from existing info...
research
11/14/2016

Traversing Knowledge Graph in Vector Space without Symbolic Space Guidance

Recent studies on knowledge base completion, the task of recovering miss...
research
06/03/2015

Traversing Knowledge Graphs in Vector Space

Path queries on a knowledge graph can be used to answer compositional qu...
research
05/26/2019

Path Ranking with Attention to Type Hierarchies

The knowledge base completion problem is the problem of inferring missin...
research
10/14/2018

Hierarchical Attention Networks for Knowledge Base Completion via Joint Adversarial Training

Knowledge Base (KB) completion, which aims to determine missing relation...
research
11/02/2018

Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations

Neural models of Knowledge Base data have typically employed composition...
research
09/19/2017

Why PairDiff works? -- A Mathematical Analysis of Bilinear Relational Compositional Operators for Analogy Detection

Representing the semantic relations that exist between two given words (...

Please sign up or login with your details

Forgot password? Click here to reset