Cite this DOI

Rao, M., Kumar, M., Vineela, M., & Jyothi, M. (2018). DISTRIBUTED REPRESENTATIONS OF AWORD: A SURVEY. *Journal of Science & Technology*, *03*(06), 59–67. https://doi.org/10.46243/jst.2018.v3.i06.pp59-67

@article{rao2018distributed,
  author    = {Rao, Mr.D.Koteswara and Kumar, Mr.T.Rathna and Vineela, Mrs.K. and Jyothi, Mrs.B.Rama},
  title     = {{DISTRIBUTED REPRESENTATIONS OF AWORD: A SURVEY}},
  journal   = {Journal of Science \& Technology},
  year      = {2018},
  month     = {nov},
  volume    = {03},
  number    = {06},
  pages     = {59--67},
  publisher = {Longman Publishers},
  issn      = {2456-5660},
  doi       = {10.46243/jst.2018.v3.i06.pp59-67},
  url       = {https://doi.org/10.46243/jst.2018.v3.i06.pp59-67},
  language  = {en},
  abstract  = {The continuous Skip-gram model, which was recently presented, is a quick and easy way to build high-quality distributed vector representations that capture a huge number of accurate syntactic and semantic word associations. We provide numerous enhancements in this study that improve the quality of the vectors as well as the training speed. We get a considerable speedup and learn more regular word representations by subsampling the frequent words. We also discuss negative sampling,which is a simple alternative to hierarchical softmax. The indifference to word order and inability to capture idiomatic phrases are two fundamental limitations of word representations. The meanings of "Canada" and "Air," for example, cannot simply be merged to become "Air Canada.}
}

TY  - JOUR
TI  - DISTRIBUTED REPRESENTATIONS OF AWORD: A SURVEY
AU  - Rao, Mr.D.Koteswara
AU  - Kumar, Mr.T.Rathna
AU  - Vineela, Mrs.K.
AU  - Jyothi, Mrs.B.Rama
JO  - Journal of Science & Technology
PY  - 2018
DA  - 2018/11/21/
VL  - 03
IS  - 06
SP  - 59
EP  - 67
PB  - Longman Publishers
SN  - 2456-5660
LA  - en
AB  - The continuous Skip-gram model, which was recently presented, is a quick and easy way to build high-quality distributed vector representations that capture a huge number of accurate syntactic and semantic word associations. We provide numerous enhancements in this study that improve the quality of the vectors as well as the training speed. We get a considerable speedup and learn more regular word representations by subsampling the frequent words. We also discuss negative sampling,which is a simple alternative to hierarchical softmax. The indifference to word order and inability to capture idiomatic phrases are two fundamental limitations of word representations. The meanings of "Canada" and "Air," for example, cannot simply be merged to become "Air Canada.
DO  - 10.46243/jst.2018.v3.i06.pp59-67
UR  - https://doi.org/10.46243/jst.2018.v3.i06.pp59-67
ER  -

{
    "type": "article-journal",
    "id": "10.46243/jst.2018.v3.i06.pp59-67",
    "DOI": "10.46243/jst.2018.v3.i06.pp59-67",
    "URL": "https://doi.org/10.46243/jst.2018.v3.i06.pp59-67",
    "title": "DISTRIBUTED REPRESENTATIONS OF AWORD: A SURVEY",
    "source": "Smart Scholars DOI Registry",
    "container-title": "Journal of Science & Technology",
    "author": [
        {
            "family": "Rao",
            "given": "Mr.D.Koteswara"
        },
        {
            "family": "Kumar",
            "given": "Mr.T.Rathna"
        },
        {
            "family": "Vineela",
            "given": "Mrs.K."
        },
        {
            "family": "Jyothi",
            "given": "Mrs.B.Rama"
        }
    ],
    "issued": {
        "date-parts": [
            [
                2018,
                11,
                21
            ]
        ]
    },
    "volume": "03",
    "issue": "06",
    "page": "59-67",
    "publisher": "Longman Publishers",
    "language": "en",
    "abstract": "The continuous Skip-gram model, which was recently presented, is a quick and easy way to build high-quality distributed vector representations that capture a huge number of accurate syntactic and semantic word associations. We provide numerous enhancements in this study that improve the quality of the vectors as well as the training speed. We get a considerable speedup and learn more regular word representations by subsampling the frequent words. We also discuss negative sampling,which is a simple alternative to hierarchical softmax. The indifference to word order and inability to capture idiomatic phrases are two fundamental limitations of word representations. The meanings of \"Canada\" and \"Air,\" for example, cannot simply be merged to become \"Air Canada.",
    "ISSN": "2456-5660"
}

From the record as registered (version 2) — the record and its history. Programs: https://registry.smartscholars.in/api.php?action=cite&doi=10.46243%2Fjst.2018.v3.i06.pp59-67 gives all four in one JSON answer.