Papers by Marcel Robeer

    1 papers
    Generating Realistic Natural Language Counterfactuals (2021.findings-emnlp)

    Copied to clipboard

    Challenge: Existing methods to explain ML tasks for natural language text are either unrealistic or introduce imperceptible changes.
    Approach: They propose a method that combines a conditional GAN and embeddings of a pretrained BERT encoder to model-agnostically generate realistic natural language text counterfactuals for explaining regression and classification tasks.
    Outcome: The proposed method outperforms baseline methods on fidelity and human judgments of naturalness across multiple datasets and multiple predictive models.

    What is GenGO?

    GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

    Information

    About
    Limitations