{"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/analysis-of-bag-of-n-grams-representations","title":"Analysis of Bag-of-n-grams Representation's Properties Based on Textual Reconstruction","arxiv_id":"1809.06502","date":"2018-09-18","proceeding":null,"authors":["Qi Huang","Zhanghao Chen","Zijie Lu","Yuan Ye"],"abstract":"Despite its simplicity, bag-of-n-grams sen- tence representation has been\nfound to excel in some NLP tasks. However, it has not re- ceived much attention\nin recent years and fur- ther analysis on its properties is necessary. We\npropose a framework to investigate the amount and type of information captured\nin a general- purposed bag-of-n-grams sentence represen- tation. We first use\nsentence reconstruction as a tool to obtain bag-of-n-grams representa- tion\nthat contains general information of the sentence. We then run prediction tasks\n(sen- tence length, word content, phrase content and word order) using the\nobtained representation to look into the specific type of information captured\nin the representation. Our analysis demonstrates that bag-of-n-grams\nrepresenta- tion does contain sentence structure level in- formation. However,\nincorporating n-grams with higher order n empirically helps little with\nencoding more information in general, except for phrase content information.","url_abs":"http://arxiv.org/abs/1809.06502v1","url_pdf":"http://arxiv.org/pdf/1809.06502v1.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":"analysis-of-bag-of-n-grams-representations","repo_url":"https://github.com/HQ01/BOWMIAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}