activity
20162021
most citedA Hybrid Convolutional Variational Autoencoder for Text Generation

46 citations · 123 across the 7 of their papers we have counts for

collaborators

16 papers

cs.CL20212 cited

Controlled Text Generation as Continuous Optimization with Multiple Constraints

Sachin Kumar, Eric Malmi, Aliaksei Severyn +1

As large-scale language model pretraining pushes the state-of-the-art in text generation, recent work has turned to controlling attributes of the text such models generate. While m…

cs.CL2020

Unsupervised Text Style Transfer with Padded Masked Language Models

Eric Malmi, Aliaksei Severyn, Sascha Rothe

We propose Masker, an unsupervised text-editing method for style transfer. To tackle cases when no parallel source-target pairs are available, we train masked language models (MLMs…

cs.CL2020

Felix: Flexible Text Editing Through Tagging and Insertion

Jonathan Mallinson, Aliaksei Severyn, Eric Malmi +1

We present Felix --- a flexible text-editing approach for generation, designed to derive the maximum benefit from the ideas of decoding with bi-directional contexts and self-superv…

cs.CL2019

Encode, Tag, Realize: High-Precision Text Editing

Eric Malmi, Sebastian Krause, Sascha Rothe +2

We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task. Target texts are reconstructed from the inputs using three main edit operati…

cs.LG20194 cited

Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities

Octavian-Eugen Ganea, Sylvain Gelly, Gary Bécigneul +1

The Softmax function on top of a final linear layer is the de facto method to output probability distributions in neural networks. In many applications such as language models or t…

cs.CL2018

Adversarial Neural Networks for Cross-lingual Sequence Tagging

Heike Adel, Anton Bryl, David Weiss +1

We study cross-lingual sequence tagging with little or no labeled data in the target language. Adversarial training has previously been shown to be effective for training cross-lin…