{"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/sequence-modeling-via-segmentations","title":"Sequence Modeling via Segmentations","arxiv_id":"1702.07463","date":"2017-02-24","proceeding":"ICML 2017 8","authors":["Chong Wang","Yining Wang","Po-Sen Huang","Abdel-rahman Mohamed","Dengyong Zhou","Li Deng"],"abstract":"Segmental structure is a common pattern in many types of sequences such as\nphrases in human languages. In this paper, we present a probabilistic model for\nsequences via their segmentations. The probability of a segmented sequence is\ncalculated as the product of the probabilities of all its segments, where each\nsegment is modeled using existing tools such as recurrent neural networks.\nSince the segmentation of a sequence is usually unknown in advance, we sum over\nall valid segmentations to obtain the final probability for the sequence. An\nefficient dynamic programming algorithm is developed for forward and backward\ncomputations without resorting to any approximation. We demonstrate our\napproach on text segmentation and speech recognition tasks. In addition to\nquantitative results, we also show that our approach can discover meaningful\nsegments in their respective application contexts.","url_abs":"http://arxiv.org/abs/1702.07463v7","url_pdf":"http://arxiv.org/pdf/1702.07463v7.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":"sequence-modeling-via-segmentations","repo_url":"https://github.com/posenhuang/NPMT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"sequence-modeling-via-segmentations","repo_url":"https://github.com/Microsoft/NPMT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"text-segmentation","task_name":"Text Segmentation"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.07463","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}