{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neural-vector-conceptualization-for-word","title":"Neural Vector Conceptualization for Word Vector Space Interpretation","arxiv_id":"1904.01500","date":"2019-04-02","proceeding":"WS 2019 6","authors":["Robert Schwarzenberg","Lisa Raithel","David Harbecke"],"abstract":"Distributed word vector spaces are considered hard to interpret which hinders\nthe understanding of natural language processing (NLP) models. In this work, we\nintroduce a new method to interpret arbitrary samples from a word vector space.\nTo this end, we train a neural model to conceptualize word vectors, which means\nthat it activates higher order concepts it recognizes in a given vector.\nContrary to prior approaches, our model operates in the original vector space\nand is capable of learning non-linear relations between word vectors and\nconcepts. Furthermore, we show that it produces considerably less entropic\nconcept activation profiles than the popular cosine similarity.","url_abs":"http://arxiv.org/abs/1904.01500v1","url_pdf":"http://arxiv.org/pdf/1904.01500v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neural-vector-conceptualization-for-word","repo_url":"https://github.com/dfki-nlp/nvc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}