{"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/aligning-vector-spaces-with-noisy-supervised","title":"Aligning Vector-spaces with Noisy Supervised Lexicons","arxiv_id":"1903.10238","date":"2019-03-25","proceeding":null,"authors":["Noa Yehezkel Lubin","Jacob Goldberger","Yoav Goldberg"],"abstract":"The problem of learning to translate between two vector spaces given a set of\naligned points arises in several application areas of NLP. Current solutions\nassume that the lexicon which defines the alignment pairs is noise-free. We\nconsider the case where the set of aligned points is allowed to contain an\namount of noise, in the form of incorrect lexicon pairs and show that this\narises in practice by analyzing the edited dictionaries after the cleaning\nprocess. We demonstrate that such noise substantially degrades the accuracy of\nthe learned translation when using current methods. We propose a model that\naccounts for noisy pairs. This is achieved by introducing a generative model\nwith a compatible iterative EM algorithm. The algorithm jointly learns the\nnoise level in the lexicon, finds the set of noisy pairs, and learns the\nmapping between the spaces. We demonstrate the effectiveness of our proposed\nalgorithm on two alignment problems: bilingual word embedding translation, and\nmapping between diachronic embedding spaces for recovering the semantic shifts\nof words across time periods.","url_abs":"http://arxiv.org/abs/1903.10238v1","url_pdf":"http://arxiv.org/pdf/1903.10238v1.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":"aligning-vector-spaces-with-noisy-supervised","repo_url":"https://github.com/NoaKel/Noise-Aware-Alignment","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.10238","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}