• Publications
  • Influence
Complex Embeddings for Simple Link Prediction
TLDR
In statistical relational learning, the link prediction problem is key to automatically understand the structure of large knowledge bases. Expand
  • 717
  • 231
  • PDF
Convolutional 2D Knowledge Graph Embeddings
TLDR
We introduce ConvE, a multi-layer convolutional network model for link prediction, and report state-of-the-art results for several established datasets. Expand
  • 497
  • 207
  • PDF
Modeling Relations and Their Mentions without Labeled Text
TLDR
We present a novel approach to distant supervision that can alleviate this problem based on the following two ideas: First, we use a factor graph to explicitly model the decision whether two entities are related, and the decisionwhether this relation is mentioned in a given sentence; second, we apply constraint-driven semi-supervision to train this model without any knowledge about which sentences express the relations in our training KB. Expand
  • 788
  • 151
  • PDF
Relation Extraction with Matrix Factorization and Universal Schemas
TLDR
We present a new approach to implicature with universal schemas and show that it outperforms state-of-the-Art distant supervision. Expand
  • 545
  • 72
  • PDF
Constructing Datasets for Multi-hop Reading Comprehension Across Documents
TLDR
We propose a novel task to encourage the development of models for text understanding across multiple documents and to investigate the limits of existing methods. Expand
  • 211
  • 45
  • PDF
Improving the Accuracy and Efficiency of MAP Inference for Markov Logic
TLDR
We present Cutting Plane Inference (CPI), a Maximum A Posteriori (MAP) inference method for Statistical Relational Learning. Expand
  • 198
  • 29
  • PDF
End-to-end Differentiable Proving
TLDR
We replace symbolic unification with a differentiable computation on vector representations of symbols using a radial basis function kernel, thereby combining symbolic reasoning with learning subsymbolic vector representations. Expand
  • 148
  • 28
  • PDF
SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications
TLDR
We describe the SemEval task of extracting keyphrases and relations between them from scientific documents, which is crucial for understanding which publications describe which processes, tasks and materials and how those relate to one another. Expand
  • 139
  • 25
  • PDF
Structured Relation Discovery using Generative Models
TLDR
We propose a series of generative probabilistic models, broadly similar to topic models, each which generates a corpus of observed triples of entity mention pairs and the surface syntactic dependency path between them. Expand
  • 128
  • 16
  • PDF
Frustratingly Short Attention Spans in Neural Language Modeling
TLDR
We propose a neural language model with a key-value attention mechanism that outputs separate representations for the key and value of a differentiable memory, as well as for encoding the next-word distribution. Expand
  • 72
  • 14
  • PDF