{"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/domain-and-function-a-dual-space-model-of","title":"Domain and Function: A Dual-Space Model of Semantic Relations and Compositions","arxiv_id":"1309.4035","date":"2013-09-16","proceeding":null,"authors":["Peter D. Turney"],"abstract":"Given appropriate representations of the semantic relations between carpenter\nand wood and between mason and stone (for example, vectors in a vector space\nmodel), a suitable algorithm should be able to recognize that these relations\nare highly similar (carpenter is to wood as mason is to stone; the relations\nare analogous). Likewise, with representations of dog, house, and kennel, an\nalgorithm should be able to recognize that the semantic composition of dog and\nhouse, dog house, is highly similar to kennel (dog house and kennel are\nsynonymous). It seems that these two tasks, recognizing relations and\ncompositions, are closely connected. However, up to now, the best models for\nrelations are significantly different from the best models for compositions. In\nthis paper, we introduce a dual-space model that unifies these two tasks. This\nmodel matches the performance of the best previous models for relations and\ncompositions. The dual-space model consists of a space for measuring domain\nsimilarity and a space for measuring function similarity. Carpenter and wood\nshare the same domain, the domain of carpentry. Mason and stone share the same\ndomain, the domain of masonry. Carpenter and mason share the same function, the\nfunction of artisans. Wood and stone share the same function, the function of\nmaterials. In the composition dog house, kennel has some domain overlap with\nboth dog and house (the domains of pets and buildings). The function of kennel\nis similar to the function of house (the function of shelters). By combining\ndomain and function similarities in various ways, we can model relations,\ncompositions, and other aspects of semantics.","url_abs":"http://arxiv.org/abs/1309.4035v1","url_pdf":"http://arxiv.org/pdf/1309.4035v1.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":"domain-and-function-a-dual-space-model-of","repo_url":"https://github.com/tigerchen52/pearl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC0-1.0"}}],"tasks":[{"task_slug":"semantic-composition","task_name":"Semantic Composition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1309.4035","atlas_url":"https://app.syntology.ai/?focus=1309.4035","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}