{"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/representation-degeneration-problem-in-1","title":"Representation Degeneration Problem in Training Natural Language Generation Models","arxiv_id":"1907.12009","date":"2019-07-28","proceeding":"ICLR 2019 5","authors":["Jun Gao","Di He","Xu Tan","Tao Qin","Li-Wei Wang","Tie-Yan Liu"],"abstract":"We study an interesting problem in training neural network-based models for natural language generation tasks, which we call the \\emph{representation degeneration problem}. We observe that when training a model for natural language generation tasks through likelihood maximization with the weight tying trick, especially with big training datasets, most of the learnt word embeddings tend to degenerate and be distributed into a narrow cone, which largely limits the representation power of word embeddings. We analyze the conditions and causes of this problem and propose a novel regularization method to address it. Experiments on language modeling and machine translation show that our method can largely mitigate the representation degeneration problem and achieve better performance than baseline algorithms.","url_abs":"https://arxiv.org/abs/1907.12009v1","url_pdf":"https://arxiv.org/pdf/1907.12009v1.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":"representation-degeneration-problem-in-1","repo_url":"https://github.com/nehalelkaref/towards-a-better-isotropy-to-detect-hatespeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"weight-tying","method_name":"Weight Tying"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.12009","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}