activity
20152022
most citedQuestEval: Summarization Asks for Fact-based Evaluation

25 citations · 76 across the 9 of their papers we have counts for

collaborators

20 papers

cs.CL20222 cited

Which Discriminator for Cooperative Text Generation?

Antoine Chaffin, Thomas Scialom, Sylvain Lamprier +4

Language models generate texts by successively predicting probability distributions for next tokens given past ones. A growing field of interest tries to leverage external informat…

cs.LG20224 cited

Generative Cooperative Networks for Natural Language Generation

Sylvain Lamprier, Thomas Scialom, Antoine Chaffin +4

Generative Adversarial Networks (GANs) have known a tremendous success for many continuous generation tasks, especially in the field of image generation. However, for discrete outp…

cs.CL2021

Skim-Attention: Learning to Focus via Document Layout

Laura Nguyen, Thomas Scialom, Jacopo Staiano +1

Transformer-based pre-training techniques of text and layout have proven effective in a number of document understanding tasks. Despite this success, multimodal pre-training models…

cs.CL20211 cited

To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs

Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier +2

Due to the discrete nature of words, language GANs require to be optimized from rewards provided by discriminator networks, via reinforcement learning methods. This is a much harde…

cs.CL202113 cited

Rethinking Automatic Evaluation in Sentence Simplification

Thomas Scialom, Louis Martin, Jacopo Staiano +2

Automatic evaluation remains an open research question in Natural Language Generation. In the context of Sentence Simplification, this is particularly challenging: the task require…

cs.CL202125 cited

QuestEval: Summarization Asks for Fact-based Evaluation

Thomas Scialom, Paul-Alexis Dray, Patrick Gallinari +4

Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments. To alleviate this iss…