{"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/learning-outside-the-box-discourse-level","title":"Learning Outside the Box: Discourse-level Features Improve Metaphor Identification","arxiv_id":"1904.02246","date":"2019-04-03","proceeding":"NAACL 2019 6","authors":["Jesse Mu","Helen Yannakoudakis","Ekaterina Shutova"],"abstract":"Most current approaches to metaphor identification use restricted linguistic\ncontexts, e.g. by considering only a verb's arguments or the sentence\ncontaining a phrase. Inspired by pragmatic accounts of metaphor, we argue that\nbroader discourse features are crucial for better metaphor identification. We\ntrain simple gradient boosting classifiers on representations of an utterance\nand its surrounding discourse learned with a variety of document embedding\nmethods, obtaining near state-of-the-art results on the 2018 VU Amsterdam\nmetaphor identification task without the complex metaphor-specific features or\ndeep neural architectures employed by other systems. A qualitative analysis\nfurther confirms the need for broader context in metaphor processing.","url_abs":"http://arxiv.org/abs/1904.02246v2","url_pdf":"http://arxiv.org/pdf/1904.02246v2.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":"learning-outside-the-box-discourse-level","repo_url":"https://github.com/jayelm/broader-metaphor","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"document-embedding","task_name":"Document Embedding"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}