{"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/parameter-sharing-between-dependency-parsers","title":"Parameter sharing between dependency parsers for related languages","arxiv_id":"1808.09055","date":"2018-08-27","proceeding":"EMNLP 2018 10","authors":["Miryam de Lhoneux","Johannes Bjerva","Isabelle Augenstein","Anders Søgaard"],"abstract":"Previous work has suggested that parameter sharing between transition-based\nneural dependency parsers for related languages can lead to better performance,\nbut there is no consensus on what parameters to share. We present an evaluation\nof 27 different parameter sharing strategies across 10 languages, representing\nfive pairs of related languages, each pair from a different language family. We\nfind that sharing transition classifier parameters always helps, whereas the\nusefulness of sharing word and/or character LSTM parameters varies. Based on\nthis result, we propose an architecture where the transition classifier is\nshared, and the sharing of word and character parameters is controlled by a\nparameter that can be tuned on validation data. This model is linguistically\nmotivated and obtains significant improvements over a monolingually trained\nbaseline. We also find that sharing transition classifier parameters helps when\ntraining a parser on unrelated language pairs, but we find that, in the case of\nunrelated languages, sharing too many parameters does not help.","url_abs":"http://arxiv.org/abs/1808.09055v2","url_pdf":"http://arxiv.org/pdf/1808.09055v2.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":"parameter-sharing-between-dependency-parsers","repo_url":"https://github.com/coastalcph/uuparser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.09055","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}