{"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/cross-lingual-annotation-projection-in-legal","title":"Cross-lingual Annotation Projection in Legal Texts","arxiv_id":null,"date":"2020-12-01","proceeding":"COLING 2020 8","authors":["Andrea Galassi","Kasper Drazewski","Marco Lippi","Paolo Torroni"],"abstract":"We study annotation projection in text classification problems where source documents are published in multiple languages and may not be an exact translation of one another. In particular, we focus on the detection of unfair clauses in privacy policies and terms of service. We present the first English-German parallel asymmetric corpus for the task at hand. We study and compare several language-agnostic sentence-level projection methods. Our results indicate that a combination of word embeddings and dynamic time warping performs best.","url_abs":"https://aclanthology.org/2020.coling-main.79","url_pdf":"https://aclanthology.org/2020.coling-main.79.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":"cross-lingual-annotation-projection-in-legal","repo_url":"https://bitbucket.org/a-galaxy/cross-lingual-annotation-projection-in-legal-texts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"dynamic-time-warping","task_name":"Dynamic Time Warping"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"dtw","method_name":"DTW"},{"method_slug":"elmo","method_name":"ELMo"}],"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}