Concepedia

N-gram Features

N-Gram Features is a type of text feature representation in natural language processing that captures contiguous sequences of n items—such as characters, syllables, words, or tokens—from a given corpus, distinguishing itself by its reliance on local sequential order and fixed-length context windows to model lexical and syntactic patterns.

391

Publications

18.9K

Citations

1.1K

Authors

402

Institutions

Publications per year

2017–2026

159

Parents

Publications

391

Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features

Matteo Pagliardini, Prakhar Gupta, Martin Jaggi · 2018 · 700 citations · Full text

, , +13

A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval

Yelong Shen, Xiaodong He, Jianfeng Gao et al. · 2014 · 687 citations

, , +16

What Yelp Fake Review Filter Might Be Doing?

Arjun Mukherjee, Vivek V. Venkataraman, Bing Liu et al. · Proceedings of the International AAAI Conference on Web and Social Media · 2021 · 556 citations · Full text

, , +13

Sentiment classification on customer feedback data

Michael Gamon · 2004 · 437 citations · Full text

, , +17

Approaches to language identification using Gaussian mixture models and shifted delta cepstral features

Pedro A. Torres‐Carrasquillo, Elliot Singer, M.A. Kohler et al. · 2002 · 393 citations

, , +15

1–5 of 391

Authors

1.1K

  1. MS
    Murat Saraçlar

    Boğaziçi University, Türkiye

    6 publications · 131 citations

    6

    h-index

  2. AG
    Alexander Gelbukh

    Instituto Politécnico Nacional, Mexico

    6 publications · 530 citations

    6

    h-index

  3. GS
    Grigori Sidorov

    Instituto Politécnico Nacional, Mexico

    4 publications · 405 citations

    4

    h-index

  4. IS
    Izhak Shafran

    Oregon Health & Science University, United States

    4 publications · 94 citations

    4

    h-index

  5. GK
    Grzegorz Kondrak

    University of Alberta, Canada

    4 publications · 127 citations

    4

    h-index

1–5 of 1.1K

Institutions

402

  1. Google (United States)

    Mountain View, United States

    10 h-index

    20 publications

    1.9K citations

  2. University of Alberta

    Edmonton, Canada

    8 h-index

    18 publications

    715 citations

  3. University of Washington

    Seattle, United States

    7 h-index

    20 publications

    774 citations

  4. University of Sheffield

    Sheffield, United Kingdom

    6 h-index

    11 publications

    812 citations

  5. University of Tübingen

    Tübingen, Germany

    6 h-index

    15 publications

    523 citations

  6. Massachusetts Institute of Technology

    Cambridge, United States

    6 h-index

    14 publications

    1.9K citations

  7. Carnegie Mellon University

    Pittsburgh, United States

    6 h-index

    11 publications

    355 citations

  8. Shanghai Jiao Tong University

    Shanghai, China

    5 h-index

    12 publications

    859 citations

1–8 of 402

Venues

  1. arXiv (Cornell University)

    Repository · 14 publications · 703 citations

    12

    h-index

  2. IEEE Access

    10 publications · 476 citations

    10

    h-index

  3. International Conference on Computational Linguistics

    Conference · 6 publications · 113 citations

    6

    h-index

  4. Procedia Computer Science

    5 publications · 593 citations

    5

    h-index

  5. 4

    h-index

1–5