{"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/neural-speed-reading-with-structural-jump-1","title":"Neural Speed Reading with Structural-Jump-LSTM","arxiv_id":"1904.00761","date":"2019-03-20","proceeding":"ICLR 2019 5","authors":["Christian Hansen","Casper Hansen","Stephen Alstrup","Jakob Grue Simonsen","Christina Lioma"],"abstract":"Recurrent neural networks (RNNs) can model natural language by sequentially\n'reading' input tokens and outputting a distributed representation of each\ntoken. Due to the sequential nature of RNNs, inference time is linearly\ndependent on the input length, and all inputs are read regardless of their\nimportance. Efforts to speed up this inference, known as 'neural speed\nreading', either ignore or skim over part of the input. We present\nStructural-Jump-LSTM: the first neural speed reading model to both skip and\njump text during inference. The model consists of a standard LSTM and two\nagents: one capable of skipping single words when reading, and one capable of\nexploiting punctuation structure (sub-sentence separators (,:), sentence end\nsymbols (.!?), or end of text markers) to jump ahead after reading a word. A\ncomprehensive experimental evaluation of our model against all five\nstate-of-the-art neural reading models shows that Structural-Jump-LSTM achieves\nthe best overall floating point operations (FLOP) reduction (hence is faster),\nwhile keeping the same accuracy or even improving it compared to a vanilla LSTM\nthat reads the whole text.","url_abs":"http://arxiv.org/abs/1904.00761v2","url_pdf":"http://arxiv.org/pdf/1904.00761v2.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":"neural-speed-reading-with-structural-jump-1","repo_url":"https://github.com/Varyn/Neural-Speed-Reading-with-Structural-Jump-LSTM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"speed","method_name":"SPEED"},{"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=1904.00761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00761"}},"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/Varyn/Neural-Speed-Reading-with-Structural-Jump-LSTM","reach":null}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"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":"28aa57bbe5ebf2d0","entry":"as_matrix","repo":"Varyn/Neural-Speed-Reading-with-Structural-Jump-LSTM","repo_kind":"official","path":"network_run.py","file_url":"https://github.com/Varyn/Neural-Speed-Reading-with-Structural-Jump-LSTM/blob/HEAD/network_run.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"28aa57bbe5ebf2d0"}},{"code_sha256_prefix":"1f8ab330958e1f45","entry":"compute_reading_percentage","repo":"Varyn/Neural-Speed-Reading-with-Structural-Jump-LSTM","repo_kind":"official","path":"network_run.py","file_url":"https://github.com/Varyn/Neural-Speed-Reading-with-Structural-Jump-LSTM/blob/HEAD/network_run.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1f8ab330958e1f45"}},{"code_sha256_prefix":"ad3a1dc5bd575d3d","entry":"agent_summaries","repo":"Varyn/Neural-Speed-Reading-with-Structural-Jump-LSTM","repo_kind":"official","path":"network_run.py","file_url":"https://github.com/Varyn/Neural-Speed-Reading-with-Structural-Jump-LSTM/blob/HEAD/network_run.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ad3a1dc5bd575d3d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}