Low-rank approximations of second-order document representations

Visa fullständig post



Permalänk

http://hdl.handle.net/10138/309458

Citation

Lagus , J , Sinkkonen , J & Klami , A 2019 , Low-rank approximations of second-order document representations . in M Bansal & A Villavicencio (eds) , Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL) . ACL , Stroudsburg, PA , pp. 634-644 , Conference on Computational Natural Language Learning , Hong Kong , Hong Kong , 03/11/2019 . https://doi.org/10.18653/v1/K19-1059

Titel: Low-rank approximations of second-order document representations
Författare: Lagus, Jarkko; Sinkkonen, Janne; Klami, Arto
Medarbetare: Bansal, Mohit
Villavicencio, Aline
Upphovmannens organisation: Department of Computer Science
Helsinki Institute for Information Technology
Utgivare: ACL
Datum: 2019-11
Språk: eng
Sidantal: 11
Tillhör serie: Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
ISBN: 978-1-950737-72-7
DOI: https://doi.org/10.18653/v1/K19-1059
Permanenta länken (URI): http://hdl.handle.net/10138/309458
Abstrakt: Document embeddings, created with methods ranging from simple heuristics to statistical and deep models, are widely applicable. Bag-of-vectors models for documents include the mean and quadratic approaches (Torki, 2018). We present evidence that quadratic statistics alone, without the mean information, can offer superior accuracy, fast document comparison, and compact document representations. In matching news articles to their comment threads, low-rank representations of only 3-4 times the size of the mean vector give most accurate matching, and in standard sentence comparison tasks, results are state of the art despite faster computation. Similarity measures are discussed, and the Frobenius product implicit in the proposed method is contrasted to Wasserstein or Bures metric from the transportation theory. We also shortly demonstrate matching of unordered word lists to documents, to measure topicality or sentiment of documents.
Subject: 113 Computer and information sciences
Referentgranskad: Ja
Licens: cc_by
Användningsbegränsning: openAccess
Parallelpublicerad version: publishedVersion


Filer under denna titel

Totalt antal nerladdningar: Laddar...

Filer Storlek Format Granska
K19_1059.pdf 2.350Mb PDF Granska/Öppna

Detta dokument registreras i samling:

Visa fullständig post