Show simple item record

dc.contributor.advisorRegina Barzilay.en_US
dc.contributor.authorWu, Menghua,M. Eng.Massachusetts Institute of Technology.en_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.en_US
dc.date.accessioned2021-03-22T17:17:14Z
dc.date.available2021-03-22T17:17:14Z
dc.date.issued2020en_US
dc.identifier.urihttps://hdl.handle.net/1721.1/130200
dc.descriptionThesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020en_US
dc.descriptionDate of graduation confirmed by MIT Registrar Office. "May 2020." Cataloged from student-submitted PDF of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 18-21).en_US
dc.description.abstractWe explore meta-learning for few-shot text classification. Meta-learning has shown strong performance in computer vision, where low-level patterns are transferable across learning tasks. However, directly applying this approach to text is challenging-lexical features highly informative for one task may be insignificant for another. Thus, rather than learning solely from words, our model also leverages their distributional signatures, which encode pertinent word occurrence patterns. Our model is trained within a meta-learning framework to map these signatures into attention scores, which are then used to weight the lexical representations of words. We demonstrate that our model consistently outperforms prototypical networks learned on lexical knowledge (Snell et al., 2017) in both few-shot text classification and relation classification by a significant margin across six benchmark datasets (20.0% on average in 1-shot classification).en_US
dc.description.statementofresponsibilityby Menghua Wu.en_US
dc.format.extent34 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsMIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectElectrical Engineering and Computer Science.en_US
dc.titleFew-shot text classification with distributional signaturesen_US
dc.typeThesisen_US
dc.description.degreeM. Eng.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.identifier.oclc1241198010en_US
dc.description.collectionM.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Scienceen_US
dspace.imported2021-03-22T17:16:44Zen_US
mit.thesis.degreeMasteren_US
mit.thesis.departmentEECSen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record