Concepedia

Subword Language Modeling

Subword Language Modeling is a language modeling approach that, as a method within natural language processing, generates and assigns probabilities to text sequences by representing words as sequences of subword units rather than whole words or individual characters, thereby balancing vocabulary richness with computational efficiency in handling out-of-vocabulary terms.

81

Publications

3.2K

Citations

245

Authors

88

Institutions

Publications per year

2017–2026

39

Parents

Publications

81

Modelling out-of-vocabulary words for robust speech recognition

Issam Bazzi, James Glass · DSpace@MIT (Massachusetts Institute of Technology) · 2002 · 195 citations · Full text

, , +12

Language Modeling with Deep Transformers

Kazuki Irie, Albert Zeyer, Ralf Schlüter et al. · 2019 · 177 citations · Full text

, , +14

Subword-based approaches for spoken document retrieval

Kenney Ng, Victor W. Zue · Speech Communication · 2000 · 175 citations · Full text

, , +13

BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages

Benjamin Heinzerling, Michael Strube · arXiv (Cornell University) · 2017 · 130 citations · Full text

, , +17

Morph-based speech recognition and modeling of out-of-vocabulary words across languages

Mathias Creutz, Teemu Hirsimäki, Mikko Kurimo et al. · ACM Transactions on Speech and Language Processing · 2007 · 127 citations

, , +17

1–5 of 81

Authors

245

  1. MK
    Mikko Kurimo

    Aalto University, Finland

    6 publications · 281 citations

    6

    h-index

  2. MS
    Murat Saraçlar

    Boğaziçi University, Türkiye

    5 publications · 252 citations

    5

    h-index

  3. CL
    Chin‐Hui Lee

    Georgia Institute of Technology, United States

    5 publications · 103 citations

    5

    h-index

  4. TH
    Teemu Hirsimäki

    Aalto University, Finland

    4 publications · 230 citations

    4

    h-index

  5. MC
    Mathias Creutz

    Aalto University, Finland

    3 publications · 214 citations

    3

    h-index

1–5 of 245

Institutions

88

  1. Johns Hopkins University

    Baltimore, United States

    6 h-index

    13 publications

    660 citations

  2. Aalto University

    Espoo, Finland

    4 h-index

    8 publications

    229 citations

  3. Massachusetts Institute of Technology

    Cambridge, United States

    4 h-index

    5 publications

    584 citations

  4. University of Cambridge

    Cambridge, United Kingdom

    4 h-index

    9 publications

    439 citations

  5. Boğaziçi University

    Istanbul, Türkiye

    3 h-index

    7 publications

    331 citations

  6. Nanyang Technological University

    Singapore, Singapore

    3 h-index

    13 publications

    674 citations

  7. AT&T (United States)

    Bedminster, United States

    3 h-index

    8 publications

    281 citations

  8. RWTH Aachen University

    Aachen, Germany

    3 h-index

    13 publications

    896 citations

1–8 of 88

Venues

  1. arXiv (Cornell University)

    Repository · 6 publications · 319 citations

    6

    h-index

  2. Speech Communication

    3 publications · 218 citations

    3

    h-index

  3. 2

    h-index

  4. Computer Speech & Language

    2 publications · 44 citations

    2

    h-index

  5. 2

    h-index

1–5