{"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/improving-reliability-of-word-similarity","title":"Improving Reliability of Word Similarity Evaluation by Redesigning Annotation Task and Performance Measure","arxiv_id":"1611.03641","date":"2016-11-11","proceeding":"WS 2016 8","authors":["Oded Avraham","Yoav Goldberg"],"abstract":"We suggest a new method for creating and using gold-standard datasets for\nword similarity evaluation. Our goal is to improve the reliability of the\nevaluation, and we do this by redesigning the annotation task to achieve higher\ninter-rater agreement, and by defining a performance measure which takes the\nreliability of each annotation decision in the dataset into account.","url_abs":"http://arxiv.org/abs/1611.03641v2","url_pdf":"http://arxiv.org/pdf/1611.03641v2.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":"improving-reliability-of-word-similarity","repo_url":"https://github.com/oavraham1/ag-evaluation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"word-similarity","task_name":"Word Similarity"}],"methods":[],"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}