{"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/n-grammer-augmenting-transformers-with-latent-1","title":"N-Grammer: Augmenting Transformers with latent n-grams","arxiv_id":"2207.06366","date":"2022-07-13","proceeding":null,"authors":["Aurko Roy","Rohan Anil","Guangda Lai","Benjamin Lee","Jeffrey Zhao","Shuyuan Zhang","Shibo Wang","Ye Zhang","Shen Wu","Rigel Swavely","Tao","Yu","Phuong Dao","Christopher Fifty","Zhifeng Chen","Yonghui Wu"],"abstract":"Transformer models have recently emerged as one of the foundational models in natural language processing, and as a byproduct, there is significant recent interest and investment in scaling these models. However, the training and inference costs of these large Transformer language models are prohibitive, thus necessitating more research in identifying more efficient variants. In this work, we propose a simple yet effective modification to the Transformer architecture inspired by the literature in statistical language modeling, by augmenting the model with n-grams that are constructed from a discrete latent representation of the text sequence. We evaluate our model, the N-Grammer on language modeling on the C4 data-set as well as text classification on the SuperGLUE data-set, and find that it outperforms several strong baselines such as the Transformer and the Primer. We open-source our model for reproducibility purposes in Jax.","url_abs":"https://arxiv.org/abs/2207.06366v1","url_pdf":"https://arxiv.org/pdf/2207.06366v1.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":"n-grammer-augmenting-transformers-with-latent-1","repo_url":"https://github.com/tensorflow/lingvo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"n-grammer-augmenting-transformers-with-latent-1","repo_url":"https://github.com/yiyixuxu/n-grammer-flax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"word-sense-disambiguation","task_name":"Word Sense Disambiguation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-dconv-head-attention","method_name":"Multi-DConv-Head Attention"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"primer","method_name":"Primer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"squared-relu","method_name":"Squared ReLU"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/common-sense-reasoning-on-record","task":"Common Sense Reasoning","dataset":"ReCoRD","model":"N-Grammer 343M","rank_in_archive_order":35,"of":45,"metrics":{"EM":"28.9","F1":"29.9"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"N-Grammer 343M","rank_in_archive_order":37,"of":82,"metrics":{"Accuracy":"68.3"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-c4","task":"Language Modelling","dataset":"C4","model":"N-Grammer 343M","rank_in_archive_order":7,"of":9,"metrics":{"Perplexity":"14.79"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-c4","task":"Language Modelling","dataset":"C4","model":"N-Grammer 288M","rank_in_archive_order":8,"of":9,"metrics":{"Perplexity":"15.01"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-commitmentbank","task":"Natural Language Inference","dataset":"CommitmentBank","model":"N-Grammer 343M","rank_in_archive_order":14,"of":20,"metrics":{"Accuracy":"67.9 ","F1":"59.7"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"N-Grammer 343M","rank_in_archive_order":73,"of":90,"metrics":{"Accuracy":"59.2%"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-boolq","task":"Question Answering","dataset":"BoolQ","model":"N-Grammer 343M","rank_in_archive_order":47,"of":65,"metrics":{"Accuracy":"65"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-copa","task":"Question Answering","dataset":"COPA","model":"N-Grammer 343M","rank_in_archive_order":56,"of":60,"metrics":{"Accuracy":"60.0"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-multirc","task":"Question Answering","dataset":"MultiRC","model":"N-Grammer 343M","rank_in_archive_order":19,"of":30,"metrics":{"EM":"11.3","F1":"62"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-words-in-context","task":"Word Sense Disambiguation","dataset":"Words in Context","model":"N-Grammer 343M","rank_in_archive_order":22,"of":37,"metrics":{"Accuracy":"56.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.06366","atlas_url":"https://app.syntology.ai/?focus=2207.06366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06366"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2207.06366"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2207.06366"},"call":"get_harvested_code_for_paper(arxiv_id=\"2207.06366\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2207.06366"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2207.06366\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2207.06366"},"call":"get_concepts_for_paper(arxiv_id=\"2207.06366\")"}],"by_repo":[{"repo":"tensorflow/lingvo","kind":"official","samples":5,"ran":5,"instrument":0,"unverified":0},{"repo":"yiyixuxu/n-grammer-flax","kind":"listed","samples":1,"ran":1,"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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2207.06366.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2207.06366.svg"},"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/yiyixuxu/n-grammer-flax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/lingvo","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6},"n_samples":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":5,"ran":5,"n_ran_checked":5,"n_instrument":0,"repositories":1},"listed":{"samples":1,"ran":1,"n_ran_checked":1,"n_instrument":0,"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":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":6,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-25","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"samples":[{"code_sha256":"6af7b11f92a34c6c","code_sha256_prefix":"6af7b11f92a34c6c","entry":"GetFlops","repo":"tensorflow/lingvo","repo_kind":"official","path":"lingvo/core/activations.py","file_url":"https://github.com/tensorflow/lingvo/blob/HEAD/lingvo/core/activations.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"activation_name:str/0/str","fixture_out_type":"int","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6af7b11f92a34c6c"}},{"code_sha256":"9ec960083b074b30","code_sha256_prefix":"9ec960083b074b30","entry":"ImportAllParams","repo":"tensorflow/lingvo","repo_kind":"official","path":"lingvo/model_imports.py","file_url":"https://github.com/tensorflow/lingvo/blob/HEAD/lingvo/model_imports.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"task_root:str/0/str, task_dirs:tuple/1/str, require_success:bool/0/bool","fixture_out_type":"bool","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9ec960083b074b30"}},{"code_sha256":"ca4beda520280fb9","code_sha256_prefix":"ca4beda520280fb9","entry":"ImportParams","repo":"tensorflow/lingvo","repo_kind":"official","path":"lingvo/model_imports.py","file_url":"https://github.com/tensorflow/lingvo/blob/HEAD/lingvo/model_imports.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model_name:str/0/str, task_root:str/0/str, require_success:bool/0/bool","fixture_out_type":"bool","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ca4beda520280fb9"}},{"code_sha256":"47af72600eb7ee27","code_sha256_prefix":"47af72600eb7ee27","entry":"get_bigram_ids","repo":"yiyixuxu/n-grammer-flax","repo_kind":"listed","path":"n_grammer_flax/n_grammer_flax.py","file_url":"https://github.com/yiyixuxu/n-grammer-flax/blob/HEAD/n_grammer_flax/n_grammer_flax.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"ids:ndarray/3/int, vocab_size:int/0/int, segment_pos:ndarray/2/int","fixture_out_type":"ArrayImpl","level_recorded_at":"2026-09-25T08:04:19.804293+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"47af72600eb7ee27"}},{"code_sha256":"e1e9fb4c30469b3c","code_sha256_prefix":"e1e9fb4c30469b3c","entry":"stateless_cache_dataset","repo":"tensorflow/lingvo","repo_kind":"official","path":"lingvo/compat.py","file_url":"https://github.com/tensorflow/lingvo/blob/HEAD/lingvo/compat.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"filename:str/0/str","fixture_out_type":"function","level_recorded_at":"2026-09-25T08:04:19.804293+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e1e9fb4c30469b3c"}},{"code_sha256":"f1ff841d96a18fdc","code_sha256_prefix":"f1ff841d96a18fdc","entry":"stateless_shuffle_dataset","repo":"tensorflow/lingvo","repo_kind":"official","path":"lingvo/compat.py","file_url":"https://github.com/tensorflow/lingvo/blob/HEAD/lingvo/compat.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"buffer_size:int/0/int, seed:int/0/int, reshuffle_each_iteration:bool/0/bool","fixture_out_type":"function","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f1ff841d96a18fdc"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c769f367b4ac7cfad5a4ee4ed4e93fe8e0404482ae3545ed762ac7209cf0254c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}