Learning to normalize text from few examples

    Research output: Contribution to conferenceAbstractOther research output

    Abstract

    I propose a text normalization model based on learning edit operations from labeled data while incorporating features induced from unlabeled text and from dictionaries. These features enable effective learning with little supervision, as demonstrated on an English tweet normalization dataset.
    Original languageEnglish
    Publication statusPublished - 2014
    EventATILA 2014 - Ghent, Belgium
    Duration: 20 Nov 201421 Nov 2014

    Conference

    ConferenceATILA 2014
    CountryBelgium
    CityGhent
    Period20/11/1421/11/14

      Fingerprint

    Cite this