{"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/combining-a-context-aware-neural-network-with","title":"Combining a Context Aware Neural Network with a Denoising Autoencoder for Measuring String Similarities","arxiv_id":"1807.06414","date":"2018-07-16","proceeding":null,"authors":["Mehdi Ben Lazreg","Morten Goodwin"],"abstract":"Measuring similarities between strings is central for many established and\nfast growing research areas including information retrieval, biology, and\nnatural language processing. The traditional approach for string similarity\nmeasurements is to define a metric over a word space that quantifies and sums\nup the differences between characters in two strings. The state-of-the-art in\nthe area has, surprisingly, not evolved much during the last few decades. The\nmajority of the metrics are based on a simple comparison between character and\ncharacter distributions without consideration for the context of the words.\nThis paper proposes a string metric that encompasses similarities between\nstrings based on (1) the character similarities between the words including.\nNon-Standard and standard spellings of the same words, and (2) the context of\nthe words. Our proposal is a neural network composed of a denoising autoencoder\nand what we call a context encoder specifically designed to find similarities\nbetween the words based on their context. The experimental results show that\nthe resulting metrics succeeds in 85.4\\% of the cases in finding the correct\nversion of a non-standard spelling among the closest words, compared to 63.2\\%\nwith the established Normalised-Levenshtein distance. Besides, we show that\nwords used in similar context are with our approach calculated to be similar\nthan words with different contexts, which is a desirable property missing in\nestablished string metrics.","url_abs":"http://arxiv.org/abs/1807.06414v1","url_pdf":"http://arxiv.org/pdf/1807.06414v1.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":"combining-a-context-aware-neural-network-with","repo_url":"https://github.com/mehdi-mbl/WordCoding","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}