• Publications
  • Influence
Convolutional 2D Knowledge Graph Embeddings
ConvE, a multi-layer convolutional network model for link prediction, is introduced and it is found that ConvE achieves state-of-the-art Mean Reciprocal Rank across most datasets.
Complex Embeddings for Simple Link Prediction
This work makes use of complex valued embeddings to solve the link prediction problem through latent factorization, and uses the Hermitian dot product, the complex counterpart of the standard dot product between real vectors.
Modeling Relations and Their Mentions without Labeled Text
A novel approach to distant supervision that can alleviate the problem of noisy patterns that hurt precision by using a factor graph and applying constraint-driven semi-supervision to train this model without any knowledge about which sentences express the relations in the authors' training KB.
Language Models as Knowledge Bases?
An in-depth analysis of the relational knowledge already present (without fine-tuning) in a wide range of state-of-the-art pretrained language models finds that BERT contains relational knowledge competitive with traditional NLP methods that have some access to oracle knowledge.
The CoNLL 2007 Shared Task on Dependency Parsing
The tasks of the different tracks are defined and how the data sets were created from existing treebanks for ten languages are described, to characterize the different approaches of the participating systems and report the test results and provide a first analysis of these results.
MLQA: Evaluating Cross-lingual Extractive Question Answering
This work presents MLQA, a multi-way aligned extractive QA evaluation benchmark intended to spur research in this area, and evaluates state-of-the-art cross-lingual models and machine-translation-based baselines onMLQA.
Relation Extraction with Matrix Factorization and Universal Schemas
This work presents matrix factorization models that learn latent feature vectors for entity tuples and relations that achieve substantially higher accuracy than a traditional classification approach and is able to reason about unstructured and structured data in mutually-supporting ways.
Constructing Datasets for Multi-hop Reading Comprehension Across Documents
A novel task to encourage the development of models for text understanding across multiple documents and to investigate the limits of existing methods, in which a model learns to seek and combine evidence — effectively performing multihop, alias multi-step, inference.
End-to-end Differentiable Proving
It is demonstrated that this architecture outperforms ComplEx, a state-of-the-art neural link prediction model, on three out of four benchmark knowledge bases while at the same time inducing interpretable function-free first-order logic rules.
SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications
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