4.8k citations · 9.5k across the 67 of their papers we have counts for
8 papers · 1 filter
A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks
Victor Sanh, Thomas Wolf, Sebastian Ruder
Much effort has been devoted to evaluate whether multi-task learning can be leveraged to learn rich representations that can be used in various Natural Language Processing (NLP) do…
Off-the-Shelf Unsupervised NMT
Chris Hokamp, Sebastian Ruder, John Glover
We frame unsupervised machine translation (MT) in the context of multi-task learning (MTL), combining insights from both directions. We leverage off-the-shelf neural MT architectur…
A Discriminative Latent-Variable Model for Bilingual Lexicon Induction
Sebastian Ruder, Ryan Cotterell, Yova Kementchedjhieva +1
We introduce a novel discriminative latent variable model for bilingual lexicon induction. Our model combines the bipartite matching dictionary prior of Haghighi et al. (2008) with…
On the Limitations of Unsupervised Bilingual Dictionary Induction
Anders Søgaard, Sebastian Ruder, Ivan Vulić
Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevert…
Strong Baselines for Neural Semi-supervised Learning under Domain Shift
Sebastian Ruder, Barbara Plank
Novel neural models have been proposed in recent years for learning under domain shift. Most models, however, only evaluate on a single task, on proprietary datasets, or compare to…
360° Stance Detection
Sebastian Ruder, John Glover, Afshin Mehrabani +1
The proliferation of fake news and filter bubbles makes it increasingly difficult to form an unbiased, balanced opinion towards a topic. To ameliorate this, we propose 360° Stance…
Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces
Isabelle Augenstein, Sebastian Ruder, Anders Søgaard
We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddi…
Universal Language Model Fine-tuning for Text Classification
Jeremy Howard, Sebastian Ruder
Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Uni…