• About
  • Policies
  • What is open access
  • Library
  • Contact
Advanced search
      View Item 
      •   BUIR Home
      • Scholarly Publications
      • Faculty of Engineering
      • Department of Electrical and Electronics Engineering
      • View Item
      •   BUIR Home
      • Scholarly Publications
      • Faculty of Engineering
      • Department of Electrical and Electronics Engineering
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Learning interpretable word embeddings via bidirectional alignment of dimensions with semantic concepts

      Thumbnail
      Embargo Lift Date: 2024-03-22
      View / Download
      901.8 Kb
      Author(s)
      Şenel, L. K.
      Şahinuç, Furkan
      Yücesoy, V.
      Schütze, H.
      Çukur, Tolga
      Koç, Aykut
      Date
      2022-03-22
      Source Title
      Information Processing & Management
      Print ISSN
      0306-4573
      Electronic ISSN
      1873-5371
      Publisher
      Elsevier Ltd
      Volume
      59
      Issue
      3
      Pages
      102925- 1 - 102925- 17
      Language
      English
      Type
      Article
      Item Usage Stats
      7
      views
      0
      downloads
      Abstract
      We propose bidirectional imparting or BiImp, a generalized method for aligning embedding dimensions with concepts during the embedding learning phase. While preserving the semantic structure of the embedding space, BiImp makes dimensions interpretable, which has a critical role in deciphering the black-box behavior of word embeddings. BiImp separately utilizes both directions of a vector space dimension: each direction can be assigned to a different concept. This increases the number of concepts that can be represented in the embedding space. Our experimental results demonstrate the interpretability of BiImp embeddings without making compromises on the semantic task performance. We also use BiImp to reduce gender bias in word embeddings by encoding gender-opposite concepts (e.g., male–female) in a single embedding dimension. These results highlight the potential of BiImp in reducing biases and stereotypes present in word embeddings. Furthermore, task or domain-specific interpretable word embeddings can be obtained by adjusting the corresponding word groups in embedding dimensions according to task or domain. As a result, BiImp offers wide liberty in studying word embeddings without any further effort.
      Keywords
      Word embeddings
      Interpretability
      Word semantics
      Permalink
      http://hdl.handle.net/11693/111493
      Published Version (Please cite this version)
      https://doi.org/10.1016/j.ipm.2022.102925
      Collections
      • Department of Electrical and Electronics Engineering 4011
      • National Magnetic Resonance Research Center (UMRAM) 301
      Show full item record

      Browse

      All of BUIRCommunities & CollectionsTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartmentsCoursesThis CollectionTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartmentsCourses

      My Account

      Login

      Statistics

      View Usage StatisticsView Google Analytics Statistics

      Bilkent University

      If you have trouble accessing this page and need to request an alternate format, contact the site administrator. Phone: (312) 290 2976
      © Bilkent University - Library IT

      Contact Us | Send Feedback | Off-Campus Access | Admin | Privacy