{"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/hierarchical-text-generation-using-an-outline","title":"Hierarchical Text Generation using an Outline","arxiv_id":"1810.08802","date":"2018-10-20","proceeding":null,"authors":["Mehdi Drissi","Olivia Watkins","Jugal Kalita"],"abstract":"Many challenges in natural language processing require generating text,\nincluding language translation, dialogue generation, and speech recognition.\nFor all of these problems, text generation becomes more difficult as the text\nbecomes longer. Current language models often struggle to keep track of\ncoherence for long pieces of text. Here, we attempt to have the model construct\nand use an outline of the text it generates to keep it focused. We find that\nthe usage of an outline improves perplexity. We do not find that using the\noutline improves human evaluation over a simpler baseline, revealing a\ndiscrepancy in perplexity and human perception. Similarly, hierarchical\ngeneration is not found to improve human evaluation scores.","url_abs":"http://arxiv.org/abs/1810.08802v1","url_pdf":"http://arxiv.org/pdf/1810.08802v1.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":"hierarchical-text-generation-using-an-outline","repo_url":"https://github.com/hmc-cs-mdrissi/fairseq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.08802","atlas_url":"https://app.syntology.ai/?focus=1810.08802","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}