{"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-to-describe-phrases-with-local-and","title":"Learning to Describe Phrases with Local and Global Contexts","arxiv_id":"1811.00266","date":"2018-11-01","proceeding":null,"authors":["Shonosuke Ishiwatari","Hiroaki Hayashi","Naoki Yoshinaga","Graham Neubig","Shoetsu Sato","Masashi Toyoda","Masaru Kitsuregawa"],"abstract":"When reading a text, it is common to become stuck on unfamiliar words and\nphrases, such as polysemous words with novel senses, rarely used idioms,\ninternet slang, or emerging entities. If we humans cannot figure out the\nmeaning of those expressions from the immediate local context, we consult\ndictionaries for definitions or search documents or the web to find other\nglobal context to help in interpretation. Can machines help us do this work?\nWhich type of context is more important for machines to solve the problem? To\nanswer these questions, we undertake a task of describing a given phrase in\nnatural language based on its local and global contexts. To solve this task, we\npropose a neural description model that consists of two context encoders and a\ndescription decoder. In contrast to the existing methods for non-standard\nEnglish explanation [Ni+ 2017] and definition generation [Noraset+ 2017;\nGadetsky+ 2018], our model appropriately takes important clues from both local\nand global contexts. Experimental results on three existing datasets (including\nWordNet, Oxford and Urban Dictionaries) and a dataset newly created from\nWikipedia demonstrate the effectiveness of our method over previous work.","url_abs":"http://arxiv.org/abs/1811.00266v2","url_pdf":"http://arxiv.org/pdf/1811.00266v2.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-to-describe-phrases-with-local-and","repo_url":"https://github.com/shonosuke/ishiwatari-naacl2019","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}