Thomas Hofmann

Generative Minimization Networks: Training GANs Without Competition

2021 · arXiv (Cornell University)

Many applications in machine learning can be framed as minimization problems and solved efficiently using gradient-based techniques. However, recent applications of generative models, particularly GANs, have triggered interest in solving min-max games for which standard …

Fully Character-Level Neural Machine Translation without Explicit Segmentation

2017 · Transactions of the Association for Computational Linguistics

Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target …

Deep Joint Entity Disambiguation with Local Neural Attention

2017

We propose a novel deep learning model for joint document-level entity disambiguation, which leverages learned neural representations. Key components are entity embeddings, a neural attention mechanism over local context windows, and a differentiable joint inference …

End-to-End Neural Entity Linking

2018

Entity Linking (EL) is an essential task for semantic text understanding and information extraction. Popular methods separately address the Mention Detection (MD) and Entity Disambiguation (ED) stages of EL, without leveraging their mutual dependency. We …