Sort by:

• Highly Influential Citations
• Citations
• Acceleration
• Velocity
• Recency

Learn More

An overview of gradient descent optimization algorithms

• Sebastian Ruder
• ArXiv
• 2016

Gradient descent optimization algorithms, while increasingly popular, are often used as black-box optimizers, as practical explanations of their strengths and weaknesses are hard to come by. This… (More)

An Overview of Multi-Task Learning in Deep Neural Networks

• Sebastian Ruder
• ArXiv
• 2017

Multi-task learning (MTL) has led to successes in many applications of machine learning, from natural language processing and speech recognition to computer vision and drug discovery. This article… (More)

Universal Language Model Fine-tuning for Text Classification

• Sebastian Ruder, Jeremy Howard
• ACL
• 2018

Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Universal Language… (More)

Sluice networks: Learning what to share between loosely related tasks

• Sebastian Ruder, Joachim Bingel, Isabelle Augenstein, Anders Søgaard
• ArXiv
• 2017

Multi-task learning is motivated by the observation that humans bring to bear what they know about related problems when solving new ones. Similarly, deep neural networks can profit from related… (More)

On the Limitations of Unsupervised Bilingual Dictionary Induction

• Anders Søgaard, Sebastian Ruder, Ivan Vulic
• ACL
• 2018

Unsupervised machine translation—i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora—seems impossible, but nevertheless, Lample et al.… (More)

Character-level and Multi-channel Convolutional Neural Networks for Large-scale Authorship Attribution

• Sebastian Ruder, Parsa Ghaffari, John G. Breslin
• ArXiv
• 2016

Convolutional neural networks (CNNs) have demonstrated superior capability for extracting information from raw signals in computer vision. Recently, characterlevel and multi-channel CNNs have… (More)

A Hierarchical Model of Reviews for Aspect-based Sentiment Analysis

• Sebastian Ruder, Parsa Ghaffari, John G. Breslin
• EMNLP
• 2016

Opinion mining from customer reviews has become pervasive in recent years. Sentences in reviews, however, are usually classified independently, even though they form part of a review’s argumentative… (More)

Fine-tuned Language Models for Text Classification

• Jeremy Howard, Sebastian Ruder
• ArXiv
• 2018

Transfer learning has revolutionized computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Fine-tuned Language Models… (More)

A survey of cross-lingual embedding models

• Sebastian Ruder
• ArXiv
• 2017

Cross-lingual embedding models allow us to project words from different languages into a shared embedding space. This allows us to apply models trained on languages with a lot of data, e.g. English… (More)

Generalizing Procrustes Analysis for Better Bilingual Dictionary Induction

• Yova Kementchedjhieva, Sebastian Ruder, Ryan Cotterell, Anders Søgaard
• CoNLL
• 2018

Most recent approaches to bilingual dictionary induction find a linear alignment between the word vector spaces of two languages. We show that projecting the two languages onto a third, latent space,… (More)

• ‹
• 1
• 2
• 3
• ›