{"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/parser-training-with-heterogeneous-treebanks","title":"Parser Training with Heterogeneous Treebanks","arxiv_id":"1805.05089","date":"2018-05-14","proceeding":"ACL 2018 7","authors":["Sara Stymne","Miryam de Lhoneux","Aaron Smith","Joakim Nivre"],"abstract":"How to make the most of multiple heterogeneous treebanks when training a\nmonolingual dependency parser is an open question. We start by investigating\npreviously suggested, but little evaluated, strategies for exploiting multiple\ntreebanks based on concatenating training sets, with or without fine-tuning. We\ngo on to propose a new method based on treebank embeddings. We perform\nexperiments for several languages and show that in many cases fine-tuning and\ntreebank embeddings lead to substantial improvements over single treebanks or\nconcatenation, with average gains of 2.0--3.5 LAS points. We argue that\ntreebank embeddings should be preferred due to their conceptual simplicity,\nflexibility and extensibility.","url_abs":"http://arxiv.org/abs/1805.05089v1","url_pdf":"http://arxiv.org/pdf/1805.05089v1.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":"parser-training-with-heterogeneous-treebanks","repo_url":"https://github.com/UppsalaNLP/uuparser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"open-question","task_name":"Open-Ended Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.05089","atlas_url":"https://app.syntology.ai/?focus=1805.05089","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}