{"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/improved-language-modeling-by-decoding-the","title":"Improved Language Modeling by Decoding the Past","arxiv_id":"1808.05908","date":"2018-08-14","proceeding":"ACL 2019 7","authors":["Siddhartha Brahma"],"abstract":"Highly regularized LSTMs achieve impressive results on several benchmark\ndatasets in language modeling. We propose a new regularization method based on\ndecoding the last token in the context using the predicted distribution of the\nnext token. This biases the model towards retaining more contextual\ninformation, in turn improving its ability to predict the next token. With\nnegligible overhead in the number of parameters and training time, our Past\nDecode Regularization (PDR) method achieves a word level perplexity of 55.6 on\nthe Penn Treebank and 63.5 on the WikiText-2 datasets using a single softmax.\nWe also show gains by using PDR in combination with a mixture-of-softmaxes,\nachieving a word level perplexity of 53.8 and 60.5 on these datasets. In\naddition, our method achieves 1.169 bits-per-character on the Penn Treebank\nCharacter dataset for character level language modeling. These results\nconstitute a new state-of-the-art in their respective settings.","url_abs":"http://arxiv.org/abs/1808.05908v4","url_pdf":"http://arxiv.org/pdf/1808.05908v4.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":[],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-modelling-on-penn-treebank-character","task":"Language Modelling","dataset":"Penn Treebank (Character Level)","model":"Past Decode Reg. + AWD-LSTM-MoS + dyn. eval.","rank_in_archive_order":6,"of":20,"metrics":{"Bit per Character (BPC)":"1.169","Number of params":"13.8M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-penn-treebank-word","task":"Language Modelling","dataset":"Penn Treebank (Word Level)","model":"Past Decode Reg. + AWD-LSTM-MoS + dyn. eval.","rank_in_archive_order":9,"of":43,"metrics":{"Params":"22M","Test perplexity":"47.3","Validation perplexity":"48.0"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset":"WikiText-2","model":"Past Decode Reg. + AWD-LSTM-MoS + dyn. eval.","rank_in_archive_order":14,"of":38,"metrics":{"Number of params":"35M","Test perplexity":"40.3","Validation perplexity":"42.0"},"uses_additional_data":false}],"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":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"27695b251de0455f0d4096ad3507dbca11b612d8bf50bcf48f4e20f476e1c2db","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}