{"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/on-training-bi-directional-neural-network","title":"On Training Bi-directional Neural Network Language Model with Noise Contrastive Estimation","arxiv_id":"1602.06064","date":"2016-02-19","proceeding":null,"authors":["Tianxing He","Yu Zhang","Jasha Droppo","Kai Yu"],"abstract":"We propose to train bi-directional neural network language model(NNLM) with\nnoise contrastive estimation(NCE). Experiments are conducted on a rescore task\non the PTB data set. It is shown that NCE-trained bi-directional NNLM\noutperformed the one trained by conventional maximum likelihood training. But\nstill(regretfully), it did not out-perform the baseline uni-directional NNLM.","url_abs":"http://arxiv.org/abs/1602.06064v3","url_pdf":"http://arxiv.org/pdf/1602.06064v3.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":"on-training-bi-directional-neural-network","repo_url":"https://bitbucket.org/cloudygoose/ptb_rescore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}