{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/investigating-linguistic-pattern-ordering-in","title":"Investigating Linguistic Pattern Ordering in Hierarchical Natural Language Generation","arxiv_id":"1809.07629","date":"2018-09-19","proceeding":null,"authors":["Shang-Yu Su","Yun-Nung Chen"],"abstract":"Natural language generation (NLG) is a critical component in spoken dialogue\nsystem, which can be divided into two phases: (1) sentence planning: deciding\nthe overall sentence structure, (2) surface realization: determining specific\nword forms and flattening the sentence structure into a string. With the rise\nof deep learning, most modern NLG models are based on a sequence-to-sequence\n(seq2seq) model, which basically contains an encoder-decoder structure; these\nNLG models generate sentences from scratch by jointly optimizing sentence\nplanning and surface realization. However, such simple encoder-decoder\narchitecture usually fail to generate complex and long sentences, because the\ndecoder has difficulty learning all grammar and diction knowledge well. This\npaper introduces an NLG model with a hierarchical attentional decoder, where\nthe hierarchy focuses on leveraging linguistic knowledge in a specific order.\nThe experiments show that the proposed method significantly outperforms the\ntraditional seq2seq model with a smaller model size, and the design of the\nhierarchical attentional decoder can be applied to various NLG systems.\nFurthermore, different generation strategies based on linguistic patterns are\ninvestigated and analyzed in order to guide future NLG research work.","url_abs":"http://arxiv.org/abs/1809.07629v1","url_pdf":"http://arxiv.org/pdf/1809.07629v1.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":"investigating-linguistic-pattern-ordering-in","repo_url":"https://github.com/MiuLab/HNLG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"MiuLab/HNLG","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0e49d276f65d5b4391d802eb80cc5bca4d3b9d6ec07beed9d8843e63c87db328","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}