{"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/extending-a-parser-to-distant-domains-using-a","title":"Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples","arxiv_id":"1805.06556","date":"2018-05-16","proceeding":"ACL 2018 7","authors":["Vidur Joshi","Matthew Peters","Mark Hopkins"],"abstract":"We revisit domain adaptation for parsers in the neural era. First we show\nthat recent advances in word representations greatly diminish the need for\ndomain adaptation when the target domain is syntactically similar to the source\ndomain. As evidence, we train a parser on the Wall Street Jour- nal alone that\nachieves over 90% F1 on the Brown corpus. For more syntactically dis- tant\ndomains, we provide a simple way to adapt a parser using only dozens of partial\nannotations. For instance, we increase the percentage of error-free\ngeometry-domain parses in a held-out set from 45% to 73% using approximately\nfive dozen training examples. In the process, we demon- strate a new\nstate-of-the-art single model result on the Wall Street Journal test set of\n94.3%. This is an absolute increase of 1.7% over the previous state-of-the-art\nof 92.6%.","url_abs":"http://arxiv.org/abs/1805.06556v1","url_pdf":"http://arxiv.org/pdf/1805.06556v1.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":"extending-a-parser-to-distant-domains-using-a","repo_url":"https://github.com/vidurj/parser-adaptation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1805.06556","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}