{"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/geometry-of-compositionality","title":"Geometry of Compositionality","arxiv_id":"1611.09799","date":"2016-11-29","proceeding":null,"authors":["Hongyu Gong","Suma Bhat","Pramod Viswanath"],"abstract":"This paper proposes a simple test for compositionality (i.e., literal usage)\nof a word or phrase in a context-specific way. The test is computationally\nsimple, relying on no external resources and only uses a set of trained word\nvectors. Experiments show that the proposed method is competitive with state of\nthe art and displays high accuracy in context-specific compositionality\ndetection of a variety of natural language phenomena (idiomaticity, sarcasm,\nmetaphor) for different datasets in multiple languages. The key insight is to\nconnect compositionality to a curious geometric property of word embeddings,\nwhich is of independent interest.","url_abs":"http://arxiv.org/abs/1611.09799v1","url_pdf":"http://arxiv.org/pdf/1611.09799v1.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":"geometry-of-compositionality","repo_url":"https://github.com/HongyuGong/Geometry-of-Compositionality","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.09799","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}