Advanced search in
Research products
arrow_drop_down
Searching FieldsTerms
Any field
arrow_drop_down
includes
arrow_drop_down
Include:
3,045 Research products, page 1 of 305

  • Open Access
  • Preprint
  • Conference object
  • QA
  • arXiv.org e-Print Archive

10
arrow_drop_down
Relevance
arrow_drop_down
  • Publication . Preprint . Conference object . 2021
    Open Access English
    Authors: 
    Emily Black; Matt Fredrikson;
    Project: NSF | SaTC: CORE: Large: Collab... (1704845)

    We introduce leave-one-out unfairness, which characterizes how likely a model's prediction for an individual will change due to the inclusion or removal of a single other person in the model's training data. Leave-one-out unfairness appeals to the idea that fair decisio...

  • Open Access
    Authors: 
    Reid, Machel; Hu, Junjie; Neubig, Graham; Matsuo, Yutaka;
    Publisher: Association for Computational Linguistics

    Reproducible benchmarks are crucial in driving progress of machine translation research. However, existing machine translation benchmarks have been mostly limited to high-resource or well-represented languages. Despite an increasing interest in low-resource machine tran...

  • Publication . Preprint . 2019
    Open Access English
    Authors: 
    Balle, Borja; Bell, James; Gascon, Adria; Nissim, Kobbi;
    Project: UKRI | The Alan Turing Institute (EP/N510129/1)

    A protocol by Ishai et al.\ (FOCS 2006) showing how to implement distributed $n$-party summation from secure shuffling has regained relevance in the context of the recently proposed \emph{shuffle model} of differential privacy, as it allows to attain the accuracy levels...

  • Open Access English
    Authors: 
    Iyyer, Mohit; Wieting, John; Gimpel, Kevin; Zettlemoyer, Luke;

    We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency parse), SCPNs are trained to produce a paraphrase of the sentence with the desired syntax. W...

  • Publication . Preprint . Conference object . 2019
    Open Access English
    Authors: 
    Suyoun Kim; Florian Metze;
    Project: NSF | Bridges: From Communities... (1445606)

    Conversational context information, higher-level knowledge that spans across sentences, can help to recognize a long conversation. However, existing speech recognition models are typically built at a sentence level, and thus it may not capture important conversational c...

  • Open Access English
    Authors: 
    Dan, Chen; Wang, Hong; Zhang, Hongyang; Zhou, Yuchen; Ravikumar, Pradeep;

    We study the low rank approximation problem of any given matrix $A$ over $\mathbb{R}^{n\times m}$ and $\mathbb{C}^{n\times m}$ in entry-wise $\ell_p$ loss, that is, finding a rank-$k$ matrix $X$ such that $\|A-X\|_p$ is minimized. Unlike the traditional $\ell_2$ setting...

  • Publication . Conference object . Preprint . 2017
    Open Access
    Authors: 
    Wang, Chaoyang; Buenaposada, Jose Miguel; Zhu, Rui; Lucey, Simon;
    Publisher: Institute of Electrical and Electronics Engineers (IEEE)

    The ability to predict depth from a single image - using recent advances in CNNs - is of increasing interest to the vision community. Unsupervised strategies to learning are particularly appealing as they can utilize much larger and varied monocular video datasets durin...

  • Open Access English
    Authors: 
    Zeyuan Allen-Zhu; Yuanzhi Li;

    Despite the empirical success of using Adversarial Training to defend deep learning models against adversarial perturbations, so far, it still remains rather unclear what the principles are behind the existence of adversarial perturbations, and what adversarial training...

  • Open Access English
    Authors: 
    Almaadeed, Noor; Elharrouss, Omar; Al-Maadeed, Somaya; Bouridane, Ahmed; Beghdadi, Azeddine;

    Human actions in videos are 3D signals. However, there are a few methods available for multiple human action recognition. For long videos, it's difficult to search within a video for a specific action and/or person. For that, this paper proposes a new technic for multip...

  • Publication . Conference object . Preprint . 2018
    Open Access English
    Authors: 
    Ma, Xuezhe; Hu, Zecong; Liu, Jingzhou; Peng, Nanyun; Neubig, Graham; Hovy, Eduard;

    We introduce a novel architecture for dependency parsing: \emph{stack-pointer networks} (\textbf{\textsc{StackPtr}}). Combining pointer networks~\citep{vinyals2015pointer} with an internal stack, the proposed model first reads and encodes the whole sentence, then builds...