{"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/ontology-aware-token-embeddings-for","title":"Ontology-Aware Token Embeddings for Prepositional Phrase Attachment","arxiv_id":"1705.02925","date":"2017-05-08","proceeding":"ACL 2017 7","authors":["Pradeep Dasigi","Waleed Ammar","Chris Dyer","Eduard Hovy"],"abstract":"Type-level word embeddings use the same set of parameters to represent all\ninstances of a word regardless of its context, ignoring the inherent lexical\nambiguity in language. Instead, we embed semantic concepts (or synsets) as\ndefined in WordNet and represent a word token in a particular context by\nestimating a distribution over relevant semantic concepts. We use the new,\ncontext-sensitive embeddings in a model for predicting prepositional phrase(PP)\nattachments and jointly learn the concept embeddings and model parameters. We\nshow that using context-sensitive embeddings improves the accuracy of the PP\nattachment model by 5.4% absolute points, which amounts to a 34.4% relative\nreduction in errors.","url_abs":"http://arxiv.org/abs/1705.02925v1","url_pdf":"http://arxiv.org/pdf/1705.02925v1.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":"ontology-aware-token-embeddings-for","repo_url":"https://github.com/pdasigi/onto-lstm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"prepositional-phrase-attachment","task_name":"Prepositional Phrase Attachment"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.02925","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}