{"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/on-multilingual-training-of-neural-dependency","title":"On Multilingual Training of Neural Dependency Parsers","arxiv_id":"1705.10209","date":"2017-05-29","proceeding":null,"authors":["Michał Zapotoczny","Paweł Rychlikowski","Jan Chorowski"],"abstract":"We show that a recently proposed neural dependency parser can be improved by\njoint training on multiple languages from the same family. The parser is\nimplemented as a deep neural network whose only input is orthographic\nrepresentations of words. In order to successfully parse, the network has to\ndiscover how linguistically relevant concepts can be inferred from word\nspellings. We analyze the representations of characters and words that are\nlearned by the network to establish which properties of languages were\naccounted for. In particular we show that the parser has approximately learned\nto associate Latin characters with their Cyrillic counterparts and that it can\ngroup Polish and Russian words that have a similar grammatical function.\nFinally, we evaluate the parser on selected languages from the Universal\nDependencies dataset and show that it is competitive with other recently\nproposed state-of-the art methods, while having a simple structure.","url_abs":"http://arxiv.org/abs/1705.10209v1","url_pdf":"http://arxiv.org/pdf/1705.10209v1.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":"on-multilingual-training-of-neural-dependency","repo_url":"https://github.com/mzapotoczny/dependency-parser","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"on-multilingual-training-of-neural-dependency","repo_url":"https://github.com/mindspore-courses/DeepNLP-models-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}