Papers › N-Grammer: Augmenting Transformers with latent n-grams

N-Grammer: Augmenting Transformers with latent n-grams

13 Jul 2022arXiv:2207.06366archive 2025-07-28

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

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 6 code samples harvested from 2 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 5 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tensorflow/lingvo officialmentioned in papertfApache-2.0Syntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
yiyixuxu/n-grammer-flax mentioned on GitHubjaxApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran

Licence: 0 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives 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” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

tensorflow/lingvo official repository 5 samples, 5 ran (0 instrument-failed) · 0 unverified
GetFlops lingvo/core/activations.py ran Apache-2.0 (permissive) · 6af7b11f92a34c6c · report fixture: signature activation_name:str/0/str · returned int · level recorded 2026-09-25
ImportAllParams lingvo/model_imports.py ran Apache-2.0 (permissive) · 9ec960083b074b30 · report fixture: signature task_root:str/0/str, task_dirs:tuple/1/str, require_success:bool/0/bool · returned bool · level recorded 2026-09-25
ImportParams lingvo/model_imports.py ran Apache-2.0 (permissive) · ca4beda520280fb9 · report fixture: signature model_name:str/0/str, task_root:str/0/str, require_success:bool/0/bool · returned bool · level recorded 2026-09-25
stateless_cache_dataset lingvo/compat.py ran Apache-2.0 (permissive) · e1e9fb4c30469b3c · report fixture: signature filename:str/0/str · returned function · level recorded 2026-09-25
stateless_shuffle_dataset lingvo/compat.py ran Apache-2.0 (permissive) · f1ff841d96a18fdc · report fixture: signature buffer_size:int/0/int, seed:int/0/int, reshuffle_each_iteration:bool/0/bool · returned function · level recorded 2026-09-25
yiyixuxu/n-grammer-flax community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_bigram_ids n_grammer_flax/n_grammer_flax.py ran Apache-2.0 (permissive) · 47af72600eb7ee27 · report fixture: signature ids:ndarray/3/int, vocab_size:int/0/int, segment_pos:ndarray/2/int · returned ArrayImpl · level recorded 2026-09-25

Tasks

Common Sense ReasoningCoreference ResolutionLanguage ModelingLanguage ModellingNatural Language InferenceQuestion AnsweringText ClassificationWord Sense Disambiguation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Common Sense Reasoning ReCoRD N-Grammer 343M EM 28.9 #35 of 45 Archive leaderboard report
Common Sense Reasoning ReCoRD N-Grammer 343M F1 29.9 #35 of 45 Archive leaderboard report
Coreference Resolution Winograd Schema Challenge N-Grammer 343M Accuracy 68.3 #37 of 82 Archive leaderboard report
Language Modelling C4 N-Grammer 343M Perplexity 14.79 #7 of 9 Archive leaderboard report
Language Modelling C4 N-Grammer 288M Perplexity 15.01 #8 of 9 Archive leaderboard report
Natural Language Inference CommitmentBank N-Grammer 343M Accuracy 67.9 #14 of 20 Archive leaderboard report
Natural Language Inference CommitmentBank N-Grammer 343M F1 59.7 #14 of 20 Archive leaderboard report
Natural Language Inference RTE N-Grammer 343M Accuracy 59.2% #73 of 90 Archive leaderboard report
Question Answering BoolQ N-Grammer 343M Accuracy 65 #47 of 65 Archive leaderboard report
Question Answering COPA N-Grammer 343M Accuracy 60.0 #56 of 60 Archive leaderboard report
Question Answering MultiRC N-Grammer 343M EM 11.3 #19 of 30 Archive leaderboard report
Question Answering MultiRC N-Grammer 343M F1 62 #19 of 30 Archive leaderboard report
Word Sense Disambiguation Words in Context N-Grammer 343M Accuracy 56.1 #22 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDepthwise ConvolutionDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-DConv-Head AttentionMulti-Head AttentionPosition-Wise Feed-Forward LayerPrimerResidual ConnectionSoftmaxSquared ReLUTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections