{"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/evaluating-unsupervised-dutch-word-embeddings","title":"Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource","arxiv_id":"1607.00225","date":"2016-07-01","proceeding":"LREC 2016 5","authors":["Stéphan Tulkens","Chris Emmery","Walter Daelemans"],"abstract":"Word embeddings have recently seen a strong increase in interest as a result\nof strong performance gains on a variety of tasks. However, most of this\nresearch also underlined the importance of benchmark datasets, and the\ndifficulty of constructing these for a variety of language-specific tasks.\nStill, many of the datasets used in these tasks could prove to be fruitful\nlinguistic resources, allowing for unique observations into language use and\nvariability. In this paper we demonstrate the performance of multiple types of\nembeddings, created with both count and prediction-based architectures on a\nvariety of corpora, in two language-specific tasks: relation evaluation, and\ndialect identification. For the latter, we compare unsupervised methods with a\ntraditional, hand-crafted dictionary. With this research, we provide the\nembeddings themselves, the relation evaluation task benchmark for use in\nfurther research, and demonstrate how the benchmarked embeddings prove a useful\nunsupervised linguistic resource, effectively used in a downstream task.","url_abs":"http://arxiv.org/abs/1607.00225v1","url_pdf":"http://arxiv.org/pdf/1607.00225v1.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":"evaluating-unsupervised-dutch-word-embeddings","repo_url":"https://github.com/clips/dutchembeddings","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"dialect-identification","task_name":"Dialect Identification"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1607.00225","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}