Papers › Language Models with Transformers

Language Models with Transformers

20 Apr 2019arXiv 2019 10arXiv:1904.09408archive 2025-07-28

Chenguang Wang, Mu Li, Alexander J. Smola

The Transformer architecture is superior to RNN-based models in computational efficiency. Recently, GPT and BERT demonstrate the efficacy of Transformer models on various NLP tasks using pre-trained language models on large-scale corpora. Surprisingly, these Transformer architectures are suboptimal for language model itself. Neither self-attention nor the positional encoding in the Transformer is able to efficiently incorporate the word-level sequential context crucial to language modeling. In this paper, we explore effective Transformer architectures for language model, including adding additional LSTM layers to better capture the sequential context while still keeping the computation efficient. We propose Coordinate Architecture Search (CAS) to find an effective architecture through iterative refinement of the model. Experimental results on the PTB, WikiText-2, and WikiText-103 show that CAS achieves perplexities between 20.42 and 34.11 on all problems, i.e. on average an improvement of 12.0 perplexity units compared to state-of-the-art LSTMs. The source code is publicly available.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1904.09408")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · fixture could not drive it.

By repository: official repository: 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cgraywang/gluon-nlp-1 officialmentioned in papermentioned on GitHubmxnet 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

2 samples harvested; 2 ran; 1 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · fixture could not drive it

Licence: 2 of the 2 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 cgraywang/gluon-nlp-1. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

detach cgraywang/gluon-nlp-1/scripts/language_model/transformer_language_model.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 53f636bb78c95254 · report
get_batch cgraywang/gluon-nlp-1/scripts/language_model/transformer_language_model.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 8e66077340340871 · report

Tasks

Computational EfficiencyLanguage ModelingLanguage ModellingNeural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling Penn Treebank (Word Level) BERT-Large-CAS Params 395M #2 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) BERT-Large-CAS Test perplexity 31.3 #2 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) BERT-Large-CAS Validation perplexity 36.1 #2 of 43 Archive leaderboard report
Language Modelling WikiText-103 BERT-Large-CAS Number of params 395M #43 of 89 Archive leaderboard report
Language Modelling WikiText-103 BERT-Large-CAS Test perplexity 20.4 #43 of 89 Archive leaderboard report
Language Modelling WikiText-103 BERT-Large-CAS Validation perplexity 19.6 #43 of 89 Archive leaderboard report
Language Modelling WikiText-2 BERT-Large-CAS Number of params 395M #10 of 38 Archive leaderboard report
Language Modelling WikiText-2 BERT-Large-CAS Test perplexity 34.1 #10 of 38 Archive leaderboard report
Language Modelling WikiText-2 BERT-Large-CAS Validation perplexity 37.7 #10 of 38 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 EncodingsAdamAttentionAttention DropoutBERTBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPTLSTMLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSigmoid ActivationSoftmaxTanh ActivationTransformerWeight DecayWordPiece

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