Learning multi-prototype word embedding from single-prototype word embedding with integrated knowledge

被引:9
|
作者
Yang, Xuefeng [1 ]
Mao, Kezhi [1 ]
机构
[1] Nanyang Technol Univ, Sch Elect & Elect Engn, Nanyang Ave, Singapore 639798, Singapore
关键词
Multi-prototype word embedding; Distributional semantic model; Fine tuning; Semantic similarity; SEMANTIC SIMILARITY;
D O I
10.1016/j.eswa.2016.03.013
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Distributional semantic models (DSM) or word embeddings are widely used in prediction of semantic similarity and relatedness. However, context aware similarity and relatedness prediction is still a challenging issue because most DSM models or word embeddings use one vector per word without considering polysemy and homonym. In this paper, we propose a supervised fine tuning framework to transform the existing single-prototype word embeddings into multi-prototype word embeddings based on lexical semantic resources. As a post-processing step, the proposed framework is compatible with any sense inventory and any word embedding. To test the proposed learning framework, both intrinsic and extrinsic evaluations are conducted. Experiments results of 3 tasks with 8 datasets show that the multi-prototype word representations learned by the proposed framework outperform single-prototype word representations. (C) 2016 Elsevier Ltd. All rights reserved.
引用
收藏
页码:291 / 299
页数:9
相关论文
共 50 条
  • [31] Learning Quality Improved Word Embedding with Assessment of Hyperparameters
    Yildiz, Beytullah
    Tezgider, Murat
    EURO-PAR 2019: PARALLEL PROCESSING WORKSHOPS, 2020, 11997 : 506 - 518
  • [32] Automatic Image Annotation using Word Embedding Learning
    Chen, Qi
    Yip, Andy M.
    Tan, Chew Lim
    2012 IEEE 24TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2012), VOL 1, 2012, : 269 - 276
  • [33] Learning Better Word Embedding by Asymmetric Low-Rank Projection of Knowledge Graph
    Tian, Fei
    Gao, Bin
    Chen, En-Hong
    Liu, Tie-Yan
    JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2016, 31 (03) : 624 - 634
  • [34] Event causality extraction through external event knowledge learning and polyhedral word embedding
    Wei, Xiao
    Huang, Chenyang
    Zhu, Nengjun
    MACHINE LEARNING, 2024, 113 (08) : 1 - 20
  • [35] Learning Better Word Embedding by Asymmetric Low-Rank Projection of Knowledge Graph
    Fei Tian
    Bin Gao
    En-Hong Chen
    Tie-Yan Liu
    Journal of Computer Science and Technology, 2016, 31 : 624 - 634
  • [36] A Framework for Multi-Prototype Based Federated Learning: Towards the Edge Intelligence
    Qiao, Yu
    Munir, Md. Shirajum
    Adhikary, Apurba
    Raha, Avi Deb
    Hong, Sang Hoon
    Hong, Choong Seon
    2023 INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING, ICOIN, 2023, : 134 - 139
  • [37] TransPhrase: A new method for generating phrase embedding from word embedding in Chinese
    Li, Rongsheng
    Huang, Shaobin
    Mao, Xiangke
    He, Jie
    Shen, Linshan
    EXPERT SYSTEMS WITH APPLICATIONS, 2021, 168
  • [38] Human Recognition with a Hardware-Accelerated Multi-Prototype Learning and Classification System
    Wicaksono, Indra Bagus
    An, Fengwei
    Mattausch, Hans Juergen
    2012 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (ROBIO 2012), 2012,
  • [39] Multi-Modal Sarcasm Detection with Sentiment Word Embedding
    Fu, Hao
    Liu, Hao
    Wang, Hongling
    Xu, Linyan
    Lin, Jiali
    Jiang, Dazhi
    ELECTRONICS, 2024, 13 (05)
  • [40] Word embedding factor based multi-head attention
    Li, Zhengren
    Zhao, Yumeng
    Zhang, Xiaohang
    Han, Huawei
    Huang, Cui
    ARTIFICIAL INTELLIGENCE REVIEW, 2025, 58 (04)