On Approximately Searching for Similar Word Embeddings

被引:0
|
作者
Sugawara, Kohei [1 ]
Kobayashi, Hayato [1 ]
Iwasaki, Masajiro [1 ]
机构
[1] Yahoo Japan Corp, Chiyoda Ku, 1-3 Kioicho, Tokyo 1028282, Japan
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We discuss an approximate similarity search for word embeddings, which is an operation to approximately find embeddings close to a given vector. We compared several metric-based search algorithms with hash-, tree-, and graph-based indexing from different aspects. Our experimental results showed that a graph-based indexing exhibits robust performance and additionally provided useful information, e.g., vector normalization achieves an efficient search with cosine similarity.
引用
收藏
页码:2265 / 2275
页数:11
相关论文
共 50 条
  • [41] Representation and Identification of Approximately Similar Event Sequences
    Martin, T. P.
    Azvine, B.
    [J]. FLEXIBLE QUERY ANSWERING SYSTEMS 2015, 2016, 400 : 87 - 99
  • [42] Graph Embeddings via Tensor Products and Approximately Orthonormal Codes
    Qiu, Frank
    [J]. arXiv, 2022,
  • [43] SMOOTH EMBEDDINGS OF HOMOLOGICALLY SIMILAR MANIFOLDS
    ROSEMAN, DM
    [J]. NOTICES OF THE AMERICAN MATHEMATICAL SOCIETY, 1969, 16 (01): : 272 - &
  • [44] SMOOTH EMBEDDINGS OF HOMOLOGICALLY SIMILAR MANIFOLDS
    ROSEMAN, DM
    [J]. TRANSACTIONS OF THE AMERICAN MATHEMATICAL SOCIETY, 1972, 174 (447) : 107 - 126
  • [45] Gender Bias in Contextualized Word Embeddings
    Zhao, Jieyu
    Wangt, Tianlu
    Yatskart, Mark
    Cotterell, Ryan
    Ordonezt, Vicente
    Chang, Kai-Wei
    [J]. 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, 2019, : 629 - 634
  • [46] Intrinsic and Extrinsic Evaluations of Word Embeddings
    Zhai, Michael
    Tan, Johnny
    Choi, Jinho D.
    [J]. THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 4282 - 4283
  • [47] Joint Multiclass Debiasing of Word Embeddings
    Popovic, Radomir
    Lemmerich, Florian
    Strohmaier, Markus
    [J]. FOUNDATIONS OF INTELLIGENT SYSTEMS (ISMIS 2020), 2020, 12117 : 79 - 89
  • [48] A Systematic Literature Review on Word Embeddings
    Gutierrez, Luis
    Keith, Brian
    [J]. TRENDS AND APPLICATIONS IN SOFTWARE ENGINEERING (CIMPS 2018), 2019, 865 : 132 - 141
  • [49] Cross-Lingual Word Embeddings
    Søgaard, Anders
    Vulić, Ivan
    Ruder, Sebastian
    Faruqui, Manaal
    [J]. Synthesis Lectures on Human Language Technologies, 2019, 12 (02): : 1 - 132
  • [50] Turkish entity discovery with word embeddings
    Kalender, Murat
    Korkmaz, Emin Erkan
    [J]. TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2017, 25 (03) : 2388 - 2398