216 citations · 514 across the 35 of their papers we have counts for
4 papers · 1 filter
Generic resources are what you need: Style transfer tasks without task-specific parallel training data
Huiyuan Lai, Antonio Toral, Malvina Nissim
Style transfer aims to rewrite a source text in a different target style while preserving its content. We propose a novel approach to this task that leverages generic resources, an…
Adapting Monolingual Models: Data can be Scarce when Language Similarity is High
Wietse de Vries, Martijn Bartelds, Malvina Nissim +1
For many (minority) languages, the resources needed to train large models are not available. We investigate the performance of zero-shot transfer learning with as little data as po…
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer
Huiyuan Lai, Antonio Toral, Malvina Nissim
Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content. We show that fine-tuning pre-trained language (GPT-2) and sequence-to…
On the interaction of automatic evaluation and task framing in headline style transfer
Lorenzo De Mattei, Michele Cafagna, Huiyuan Lai +3
An ongoing debate in the NLG community concerns the best way to evaluate systems, with human evaluation often being considered the most reliable method, compared to corpus-based me…