IDEAS home Printed from https://ideas.repec.org/a/nat/nathum/v6y2022i7d10.1038_s41562-022-01316-8.html
   My bibliography  Save this article

Semantic projection recovers rich human knowledge of multiple object features from word embeddings

Author

Listed:
  • Gabriel Grand

    (MIT
    MIT)

  • Idan Asher Blank

    (UCLA
    UCLA)

  • Francisco Pereira

    (National Institute of Mental Health)

  • Evelina Fedorenko

    (MIT
    MIT)

Abstract

How is knowledge about word meaning represented in the mental lexicon? Current computational models infer word meanings from lexical co-occurrence patterns. They learn to represent words as vectors in a multidimensional space, wherein words that are used in more similar linguistic contexts—that is, are more semantically related—are located closer together. However, whereas inter-word proximity captures only overall relatedness, human judgements are highly context dependent. For example, dolphins and alligators are similar in size but differ in dangerousness. Here, we use a domain-general method to extract context-dependent relationships from word embeddings: ‘semantic projection’ of word-vectors onto lines that represent features such as size (the line connecting the words ‘small’ and ‘big’) or danger (‘safe’ to ‘dangerous’), analogous to ‘mental scales’. This method recovers human judgements across various object categories and properties. Thus, the geometry of word embeddings explicitly represents a wealth of context-dependent world knowledge.

Suggested Citation

  • Gabriel Grand & Idan Asher Blank & Francisco Pereira & Evelina Fedorenko, 2022. "Semantic projection recovers rich human knowledge of multiple object features from word embeddings," Nature Human Behaviour, Nature, vol. 6(7), pages 975-987, July.
    • Handle: RePEc:nat:nathum:v:6:y:2022:i:7:d:10.1038_s41562-022-01316-8
    DOI: 10.1038/s41562-022-01316-8
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41562-022-01316-8
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.
    File URL: https://libkey.io/10.1038/s41562-022-01316-8?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Alina Arseniev-Koehler & Jacob G. Foster, 2022. "Machine Learning as a Model for Cultural Learning: Teaching an Algorithm What it Means to be Fat," Sociological Methods & Research, , vol. 51(4), pages 1484-1539, November.
    2. Pinus, Michael & Halperin, Eran & Cao, Yajun & Coman, Alin & Gross, James & Goldenberg, Amit, 2023. "Emotion Regulation Contagion," OSF Preprints km6r4, Center for Open Science.
    3. Hong Huang & Hua Zhu & Wenshi Liu & Hua Gao & Hai Jin & Bang Liu, 2024. "Uncovering the essence of diverse media biases from the semantic embedding space," Palgrave Communications, Palgrave Macmillan, vol. 11(1), pages 1-12, December.
    4. Bei Yan & Feng Mai & Chaojiang Wu & Rui Chen & Xiaolin Li, 2024. "A Computational Framework for Understanding Firm Communication During Disasters," Information Systems Research, INFORMS, vol. 35(2), pages 590-608, June.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:nathum:v:6:y:2022:i:7:d:10.1038_s41562-022-01316-8. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.