{"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-semantic-composition-with-offset","title":"Improving Semantic Composition with Offset Inference","arxiv_id":"1704.06692","date":"2017-04-21","proceeding":"ACL 2017 7","authors":["Thomas Kober","Julie Weeds","Jeremy Reffin","David Weir"],"abstract":"Count-based distributional semantic models suffer from sparsity due to\nunobserved but plausible co-occurrences in any text collection. This problem is\namplified for models like Anchored Packed Trees (APTs), that take the\ngrammatical type of a co-occurrence into account. We therefore introduce a\nnovel form of distributional inference that exploits the rich type structure in\nAPTs and infers missing data by the same mechanism that is used for semantic\ncomposition.","url_abs":"http://arxiv.org/abs/1704.06692v1","url_pdf":"http://arxiv.org/pdf/1704.06692v1.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-semantic-composition-with-offset","repo_url":"https://github.com/tttthomasssss/acl2017","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"semantic-composition","task_name":"Semantic Composition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}