Papers by Tomoe Mizutani

    1 papers
    Surfer100: Generating Surveys From Web Resources, Wikipedia-style (2022.lrec-1)

    Copied to clipboard

    Challenge: Recent work on Wikipedia page generation focuses on generating the initial leading paragraph of a page, while recent pretrained language models improve upon both extractive and abstractive steps of previous models.
    Approach: They propose a pretrained language model that can be combined to generate Wikipedia-style summaries with sections using 100 reference human-collected surveys.
    Outcome: The proposed approach is compared with existing methods with 100 human-collected surveys.

    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