home.social

#wordembeddings — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #wordembeddings, aggregated by home.social.

fetched live
  1. 🧠📊 How can we measure imageability in literary texts?
    The authors approach how words evoke sensory experience and test whether multimodal #WordEmbeddings can better capture #imageability, #visuality, and #concreteness than text-only models, from words to sentences to poems.
    #CCLS2025 #JCLS #CLS

  2. 🧠📊 How can we measure imageability in literary texts?
    The authors approach how words evoke sensory experience and test whether multimodal #WordEmbeddings can better capture #imageability, #visuality, and #concreteness than text-only models, from words to sentences to poems.
    #CCLS2025 #JCLS #CLS

  3. It's already the last talk of #CCLS2025 😱

    Yuri Bizzoni, Pascale Feldkamp, Kristoffer L. Nielbo: Encoding Imagism? Measuring Literary Imageability, Visuality and Concreteness via Multimodal Word Embeddings (doi.org/10.26083/tuprints-0003)
    #Measuring #LiteraryImageability #WordEmbeddings

  4. It's already the last talk of #CCLS2025 😱

    Yuri Bizzoni, Pascale Feldkamp, Kristoffer L. Nielbo: Encoding Imagism? Measuring Literary Imageability, Visuality and Concreteness via Multimodal Word Embeddings (doi.org/10.26083/tuprints-0003)
    #Measuring #LiteraryImageability #WordEmbeddings

  5. Published at #IRRJ: "Graph Embeddings to Empower Entity Retrieval" by Emma J. Gerritse, Faegheh Hasibi, and Arjen P. de Vries. #EntityRetrieval, #KnowledgeGraphEmbeddings, #WordEmbeddings

    doi.org/10.54195/irrj.19877

  6. Next stop in our NLP timeline is 2013, the introduction of low dimensional dense word vectors - so-called "word embeddings" - based on distributed semantics, as e.g. word2vec by Mikolov et al. from Google, which enabled representation learning on text.

    T. Mikolov et al. (2013). Efficient Estimation of Word Representations in Vector Space.
    arxiv.org/abs/1301.3781

    #NLP #AI #wordembeddings #word2vec #ise2025 #historyofscience @fiz_karlsruhe @fizise @tabea @sourisnumerique @enorouzi

  7. Next stop in our NLP timeline is 2013, the introduction of low dimensional dense word vectors - so-called "word embeddings" - based on distributed semantics, as e.g. word2vec by Mikolov et al. from Google, which enabled representation learning on text.

    T. Mikolov et al. (2013). Efficient Estimation of Word Representations in Vector Space.
    arxiv.org/abs/1301.3781

    #NLP #AI #wordembeddings #word2vec #ise2025 #historyofscience @fiz_karlsruhe @fizise @tabea @sourisnumerique @enorouzi

  8. For the possibly vanishingly small number of people it might interest: Made a presentation on User Research and semantic vectors/word embeddings from AI, speculatively exploring possible applications: youtu.be/tPiv4LpZCvU

    #userresearch #UX #AI #wordembeddings

  9. For the possibly vanishingly small number of people it might interest: Made a presentation on User Research and semantic vectors/word embeddings from AI, speculatively exploring possible applications: youtu.be/tPiv4LpZCvU

    #userresearch #UX #AI #wordembeddings

  10. In 2013, Mikolov et al. (from Google) published word2vec, a neural network based framework to learn distributed representations of words as dense vectors in continuous space, aka word embeddings.

    T. Mikolov et al. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv:1301.3781
    arxiv.org/abs/1301.3781

    #HistoryOfAI #AI #ise2024 #lecture #distributionalsemantics #wordembeddings #embeddings @sourisnumerique @enorouzi @fizise

  11. In 2013, Mikolov et al. (from Google) published word2vec, a neural network based framework to learn distributed representations of words as dense vectors in continuous space, aka word embeddings.

    T. Mikolov et al. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv:1301.3781
    arxiv.org/abs/1301.3781

    #HistoryOfAI #AI #ise2024 #lecture #distributionalsemantics #wordembeddings #embeddings @sourisnumerique @enorouzi @fizise

  12. In lecture 05 of our #ise2024 lecture series, we are introducing the concept of distributed semantics and are referring (amongst others) to Ludwig Wittgenstein and his approach to the philosophy of language, and combine it with the idea of word vectors and embeddings.

    lecture slides: drive.google.com/file/d/1WcVlk

    #wittgenstein #nlp #wordembeddings #distributionalsemantics #lecture @fiz_karlsruhe @fizise @enorouzi @shufan @sourisnumerique #aiart #generativeai

  13. In lecture 05 of our #ise2024 lecture series, we are introducing the concept of distributed semantics and are referring (amongst others) to Ludwig Wittgenstein and his approach to the philosophy of language, and combine it with the idea of word vectors and embeddings.

    lecture slides: drive.google.com/file/d/1WcVlk

    #wittgenstein #nlp #wordembeddings #distributionalsemantics #lecture @fiz_karlsruhe @fizise @enorouzi @shufan @sourisnumerique #aiart #generativeai

  14. Next important step in our brief history of (large) #languagemodels is the use of word embeddings, i.e. mapping words onto dense vector spaces while preserving their semantics in terms of vector distances allowing for analogies via vector arithmetics.
    In 2013 Word2Vec was introduced by Mikolov et al.
    Slides: drive.google.com/file/d/1atNvM
    @fizise #llm #ai #artificialintelligence #wordembeddings #machinelearning #lecture

  15. Next important step in our brief history of (large) #languagemodels is the use of word embeddings, i.e. mapping words onto dense vector spaces while preserving their semantics in terms of vector distances allowing for analogies via vector arithmetics.
    In 2013 Word2Vec was introduced by Mikolov et al.
    Slides: drive.google.com/file/d/1atNvM
    @fizise #llm #ai #artificialintelligence #wordembeddings #machinelearning #lecture

  16. In this [Computerphile] video Robert Miles shows how the latest generation of chatbot AI can be glitched into doing the weirdest things
    youtu.be/WO2X3oZEJOA

  17. In this [Computerphile] video Robert Miles shows how the latest generation of chatbot AI can be glitched into doing the weirdest things #ChatGPT #AI #GenerativeAI #ArtificialIntelligence #chatbot #WordEmbeddings
    youtu.be/WO2X3oZEJOA

  18. 🚀 Sehr cool! Der Band zum #DFG-Symposium "#Digitale #Literaturwissenschaft", herausgegeben von @fotis_jannidis, ist erschienen! 848 Seiten stark und #OpenAccess! link.springer.com/book/10.1007 – Es geht um Literatur und Digitalität, Digitale #Edition, #Annotation, Quantitative #Textanalyse und Literaturwissenschaft und #Bibliothek. – Von mir dabei, ein Beitrag zu #WordEmbeddings für die Literaturwissenschaft: doi.org/10.1007/978-3-476-0588#CLS #DH

  19. 🚀 Sehr cool! Der Band zum #DFG-Symposium "#Digitale #Literaturwissenschaft", herausgegeben von @fotis_jannidis, ist erschienen! 848 Seiten stark und #OpenAccess! link.springer.com/book/10.1007 – Es geht um Literatur und Digitalität, Digitale #Edition, #Annotation, Quantitative #Textanalyse und Literaturwissenschaft und #Bibliothek. – Von mir dabei, ein Beitrag zu #WordEmbeddings für die Literaturwissenschaft: doi.org/10.1007/978-3-476-0588#CLS #DH

  20. Leseempfehlung zum Thema #KI: @hannesbajohr im #Merkur. Weshalb #DALLE2 die bedeutsamere Entwicklung darstellt als #GPT3, wieso #WordEmbeddings basierte Systeme (bislang) Korrelationen, aber nicht Intentionen (und Kausalitäten) reproduzieren können und wie #KI menschlichen Nutzenden "dumme Bedeutung" aufzwingt: hannesbajohr.de/wp-content/upl

  21. Zu Weihnachten gibt es einen neuen #Tuwort-Podcast. In Nummer 8 sprachen wir über die Vermessung des Klassenbegriffs mittels #WordEmbeddings, über die angeblich imperial motivierte Unterdrückung des Österreichischen #Hochdeutsch und über #LeichteSprache in der Wissenschaftskommunikation. Daneben geht es um lachende Roboter, das Wort des Jahres und GPT-3. Viel Spaß beim Reinhören!

    Link zur Folge:
    tuwort.com/index.php/2022/12/2

    Feed:
    tuwort.com/index.php/feed/mp3/

  22. Zu Weihnachten gibt es einen neuen #Tuwort-Podcast. In Nummer 8 sprachen wir über die Vermessung des Klassenbegriffs mittels #WordEmbeddings, über die angeblich imperial motivierte Unterdrückung des Österreichischen #Hochdeutsch und über #LeichteSprache in der Wissenschaftskommunikation. Daneben geht es um lachende Roboter, das Wort des Jahres und GPT-3. Viel Spaß beim Reinhören!

    Link zur Folge:
    tuwort.com/index.php/2022/12/2

    Feed:
    tuwort.com/index.php/feed/mp3/

  23. Der #tuwort-Podcast Nr. 8 ist erschienen: Wir sprechen über #GPT3, lachende #Roboter, #Zeitenwende, #WordEmbeddings zur Vermessung von Kultur, Österreichischen #Standard und #LeichteSprache in der Wissenschaftskommunikation. Mit Sandra, @josch und mir. tuwort.com/index.php/2022/12/2 @tuwort

  24. Der #tuwort-Podcast Nr. 8 ist erschienen: Wir sprechen über #GPT3, lachende #Roboter, #Zeitenwende, #WordEmbeddings zur Vermessung von Kultur, Österreichischen #Standard und #LeichteSprache in der Wissenschaftskommunikation. Mit Sandra, @josch und mir. tuwort.com/index.php/2022/12/2 @tuwort

  25. Something I have used a lot this year and is excellent github.com/RichardScottOZ/geos - a fork of the original with a few updates and also doing some things in - it is really well done and has pretty good models available too - with a Canada focus. I would have put a million documents through it roughly.

  26. This looks brilliant! Preprint on "Boosting word frequencies in authorship attribution" by Maciej Eder. Instead of relative frequencies, frequency normalisation against a background of semantically similar words was performed. Significant performance gains shown via fascinating heatmaps. See: arxiv.org/abs/2211.01289 #stylometry #AuthorshipAttribution #stylo #Kraków #CHR2022 #WordEmbeddings #Heatmaps #BurrowsDelta #CosineDelta

  27. #introduction

    Part of the Migration. Moved from @[email protected]

    Interested in #topology (for fun and #TDA )
    #GraphicalLinearAlgebra and similar notations like string diagrams and #ExistentialGraphs
    #CurryHowardIsomorphism
    #Semantics for humans and computers
    #topoi
    #CategoryTheory
    #WordEmbeddings (in #NLP )
    #language
    #logic
    #SFF
    #History of science, math, societies
    etc.

    Trans rights are human rights; blm; workers solidarity; native rights; and all the various other ways of not being vile to people

  28. #introduction

    Part of the Migration. Moved from @[email protected]

    Interested in #topology (for fun and #TDA )
    #GraphicalLinearAlgebra and similar notations like string diagrams and #ExistentialGraphs
    #CurryHowardIsomorphism
    #Semantics for humans and computers
    #topoi
    #CategoryTheory
    #WordEmbeddings (in #NLP )
    #language
    #logic
    #SFF
    #History of science, math, societies
    etc.

    Trans rights are human rights; blm; workers solidarity; native rights; and all the various other ways of not being vile to people

  29. CW: From birdsite

    Very nice work!
    ---
    RT @HammerLabML
    SAME? SAME!
    This week in the lab, Sarah Schröder presented "Scoring Association Means of word embeddings". This score quantifies bias in #WordEmbeddings, it's #trustworthy and performs comparably between different embedding spaces. ✅
    @arxiv preprint: arxiv.org/abs/2111.07864
    twitter.com/HammerLabML/status