• Publications
  • Influence
Language Models as Knowledge Bases?
TLDR
We present 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. Expand
  • 215
  • 37
  • PDF
MLQA: Evaluating Cross-lingual Extractive Question Answering
TLDR
We present MLQA, a multi-way aligned extractive QA evaluation benchmark intended to spur research in this area, and also provide machine-translation-based baselines. Expand
  • 73
  • 27
  • PDF
Neural Architectures for Fine-grained Entity Type Classification
TLDR
In this work, we investigate several neural network architectures for fine-grained entity type classification. Expand
  • 72
  • 20
  • PDF
Knowledge Graph Completion via Complex Tensor Factorization
TLDR
We reconcile both expressiveness and complexity through the use of complex-valued embeddings and explore the link between them and unitary diagonalization. Expand
  • 102
  • 18
  • PDF
Spoken Language Understanding in dialogue systems, using a 2-layer Markov Logic Network: improving semantic accuracy
TLDR
We describe a two layer Markov Logic Network (MLN) model for the Spoken Language Understanding (SLU) task in dialogue systems. Expand
  • 12
  • 1
  • PDF
The SUMMA Platform Prototype
TLDR
We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring. Expand
  • 4
  • 1
  • PDF
Investigation of alkali metal polyfluorides by matrix-isolation spectroscopy
IR laser ablation was used for the systematic matrix-isolation investigation of reaction products of alkali metal fluorides and fluorine. New insights about periodic trends in the reaction behaviourExpand
  • 13
  • PDF
Platinum fluorides beyond PtF6
Abstract Quantum-chemical calculations at DFT B3LYP and ab initio MP2, CCSD, and CCSD(T) levels have been performed on various binary fluorides of platinum up to formal oxidation state +VIII, toExpand
  • 12
Jack the Reader - A Machine Reading Framework
TLDR
We present Jack the Reader (Jack), a framework for Machine Reading that allows for quick model prototyping by component reuse, evaluation of new models on existing datasets as well as integrating new datasets and applying them on a growing set of implemented baseline models. Expand
  • 6
  • PDF
A new democratic phase coherent data-scatter technique for calibration, measurement, fingerprinting and rapid archival identification of ultraviolet-visible multi-component food spectra
The new theory of democratic phase coherent data-scatter (DPCD-S) is introduced. Basics of UV-visible spectrometry theory and error propagation have been presented. The qualitative spectral analysisExpand
  • 5