{"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/semantically-conditioned-lstm-based-natural","title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems","arxiv_id":"1508.01745","date":"2015-08-07","proceeding":"EMNLP 2015 9","authors":["Tsung-Hsien Wen","Milica Gasic","Nikola Mrksic","Pei-Hao Su","David Vandyke","Steve Young"],"abstract":"Natural language generation (NLG) is a critical component of spoken dialogue\nand it has a significant impact both on usability and perceived quality. Most\nNLG systems in common use employ rules and heuristics and tend to generate\nrigid and stylised responses without the natural variation of human language.\nThey are also not easily scaled to systems covering multiple domains and\nlanguages. This paper presents a statistical language generator based on a\nsemantically controlled Long Short-term Memory (LSTM) structure. The LSTM\ngenerator can learn from unaligned data by jointly optimising sentence planning\nand surface realisation using a simple cross entropy training criterion, and\nlanguage variation can be easily achieved by sampling from output candidates.\nWith fewer heuristics, an objective evaluation in two differing test domains\nshowed the proposed method improved performance compared to previous methods.\nHuman judges scored the LSTM system higher on informativeness and naturalness\nand overall preferred it to the other systems.","url_abs":"http://arxiv.org/abs/1508.01745v2","url_pdf":"http://arxiv.org/pdf/1508.01745v2.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":"semantically-conditioned-lstm-based-natural","repo_url":"https://github.com/andy194673/nlg-sclstm-multiwoz","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"semantically-conditioned-lstm-based-natural","repo_url":"https://github.com/mrcmoresi/sc-lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"informativeness","task_name":"Informativeness"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"spoken-dialogue-systems","task_name":"Spoken Dialogue Systems"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1508.01745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1508.01745"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mrcmoresi/sc-lstm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/andy194673/nlg-sclstm-multiwoz","reach":null}],"summary":{"ran_honours":4,"ran_draft_wrong":3},"by_repo_kind":{"listed":{"samples":7,"ran":7,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"c12514be986c9428","entry":"evaluate","repo":"mrcmoresi/sc-lstm","repo_kind":"listed","path":"run_woz3.py","file_url":"https://github.com/mrcmoresi/sc-lstm/blob/HEAD/run_woz3.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c12514be986c9428"}},{"code_sha256_prefix":"225f381678eb983a","entry":"evaluate","repo":"andy194673/nlg-sclstm-multiwoz","repo_kind":"listed","path":"run_woz3.py","file_url":"https://github.com/andy194673/nlg-sclstm-multiwoz/blob/HEAD/run_woz3.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"225f381678eb983a"}},{"code_sha256_prefix":"771b8d83423da0b0","entry":"get_slot_error","repo":"mrcmoresi/sc-lstm","repo_kind":"listed","path":"run_woz3.py","file_url":"https://github.com/mrcmoresi/sc-lstm/blob/HEAD/run_woz3.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"771b8d83423da0b0"}},{"code_sha256_prefix":"ed3de5a69932a38f","entry":"get_slot_error","repo":"andy194673/nlg-sclstm-multiwoz","repo_kind":"listed","path":"run_woz3.py","file_url":"https://github.com/andy194673/nlg-sclstm-multiwoz/blob/HEAD/run_woz3.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed3de5a69932a38f"}},{"code_sha256_prefix":"faf421c0fe195b81","entry":"score","repo":"mrcmoresi/sc-lstm","repo_kind":"listed","path":"run_woz3.py","file_url":"https://github.com/mrcmoresi/sc-lstm/blob/HEAD/run_woz3.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"faf421c0fe195b81"}},{"code_sha256_prefix":"2d9e4c619f62021f","entry":"score","repo":"andy194673/nlg-sclstm-multiwoz","repo_kind":"listed","path":"run_woz3.py","file_url":"https://github.com/andy194673/nlg-sclstm-multiwoz/blob/HEAD/run_woz3.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d9e4c619f62021f"}},{"code_sha256_prefix":"f5a233167ed9efc4","entry":"score_woz3","repo":"andy194673/nlg-sclstm-multiwoz","repo_kind":"listed","path":"bleu.py","file_url":"https://github.com/andy194673/nlg-sclstm-multiwoz/blob/HEAD/bleu.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f5a233167ed9efc4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}