{"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/srl4orl-improving-opinion-role-labeling-using","title":"SRL4ORL: Improving Opinion Role Labeling using Multi-task Learning with Semantic Role Labeling","arxiv_id":"1711.00768","date":"2017-11-02","proceeding":"NAACL 2018 6","authors":["Ana Marasović","Anette Frank"],"abstract":"For over a decade, machine learning has been used to extract\nopinion-holder-target structures from text to answer the question \"Who\nexpressed what kind of sentiment towards what?\". Recent neural approaches do\nnot outperform the state-of-the-art feature-based models for Opinion Role\nLabeling (ORL). We suspect this is due to the scarcity of labeled training data\nand address this issue using different multi-task learning (MTL) techniques\nwith a related task which has substantially more data, i.e. Semantic Role\nLabeling (SRL). We show that two MTL models improve significantly over the\nsingle-task model for labeling of both holders and targets, on the development\nand the test sets. We found that the vanilla MTL model which makes predictions\nusing only shared ORL and SRL features, performs the best. With deeper analysis\nwe determine what works and what might be done to make further improvements for\nORL.","url_abs":"http://arxiv.org/abs/1711.00768v3","url_pdf":"http://arxiv.org/pdf/1711.00768v3.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":"srl4orl-improving-opinion-role-labeling-using","repo_url":"https://github.com/amarasovic/naacl-mpqa-srl4orl","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"fine-grained-opinion-analysis","task_name":"Fine-Grained Opinion Analysis"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-opinion-analysis-on-mpqa","task":"Fine-Grained Opinion Analysis","dataset":"MPQA","model":"FS-MTL","rank_in_archive_order":2,"of":3,"metrics":{"Holder Binary F1":"83.80","Target Binary F1":"72.06"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.00768","atlas_url":"https://app.syntology.ai/?focus=1711.00768","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}