Advanced search in Research products
Research products
Searching FieldsTerms
Any field
The following results are related to Digital Humanities and Cultural Heritage. Are you interested to view more results? Visit OpenAIRE - Explore.
2 Research products, page 1 of 1

  • Digital Humanities and Cultural Heritage
  • Publications
  • Other research products
  • Preprint
  • Netherlands Organisation for Scientific Research (NWO)
  • SPuDisc: Searching Public Discourse
  • Semantic Search in E-Discovery

Date (most recent)
  • Publication . Article . Conference object . Preprint . 2016
    Open Access
    Kenter, T.; Borisov, A.; de Rijke, M.; Erk, K.; Smith, N.A.;
    Publisher: Association for Computational Linguistics
    Country: Netherlands
    Project: EC | VOX-POL (312827), NWO | Modeling and Learning fro... (2300171779), NWO | SPuDisc: Searching Public... (2300176811), NWO | Semantic Search in E-Disc... (2300168486)

    We present the Siamese Continuous Bag of Words (Siamese CBOW) model, a neural network for efficient estimation of high-quality sentence embeddings. Averaging the embeddings of words in a sentence has proven to be a surprisingly successful and efficient way of obtaining sentence embeddings. However, word embeddings trained with the methods currently available are not optimized for the task of sentence representation, and, thus, likely to be suboptimal. Siamese CBOW handles this problem by training word embeddings directly for the purpose of being averaged. The underlying neural network learns word embeddings by predicting, from a sentence representation, its surrounding sentences. We show the robustness of the Siamese CBOW model by evaluating it on 20 datasets stemming from a wide variety of sources. Accepted as full paper at ACL 2016, Berlin. 11 pages

  • Publication . Article . Preprint . 2013 . Embargo End Date: 01 Jan 2013
    Open Access
    Zoghi, M.; Whiteson, S.; Munos, R.; de Rijke, M.;
    Publisher: arXiv
    Project: NWO | SPuDisc: Searching Public... (2300176811), NWO | Semantic Search in E-Disc... (2300168486), NWO | Digging archaeology data:... (2300186891), NWO | Modeling and Learning fro... (2300171779), EC | COMPLACS (270327), EC | LIMOSINE (288024), NWO | Building Rich Links to En... (2300153702)

    This paper proposes a new method for the K-armed dueling bandit problem, a variation on the regular K-armed bandit problem that offers only relative feedback about pairs of arms. Our approach extends the Upper Confidence Bound algorithm to the relative setting by using estimates of the pairwise probabilities to select a promising arm and applying Upper Confidence Bound with the winner as a benchmark. We prove a finite-time regret bound of order O(log t). In addition, our empirical results using real data from an information retrieval application show that it greatly outperforms the state of the art. Comment: 13 pages, 6 figures