Papers › Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale

Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale

13 Mar 2024arXiv:2403.08293archive 2025-07-28

Xiang Hu, Pengyu Ji, Qingyang Zhu, Wei Wu, Kewei Tu

A syntactic language model (SLM) incrementally generates a sentence with its syntactic tree in a left-to-right manner. We present Generative Pretrained Structured Transformers (GPST), an unsupervised SLM at scale capable of being pre-trained from scratch on raw texts with high parallelism. GPST circumvents the limitations of previous SLMs such as relying on gold trees and sequential training. It consists of two components, a usual SLM supervised by a uni-directional language modeling loss, and an additional composition model, which induces syntactic parse trees and computes constituent representations, supervised by a bi-directional language modeling loss. We propose a representation surrogate to enable joint parallel training of the two models in a hard-EM fashion. We pre-train GPST on OpenWebText, a corpus with $9$ billion tokens, and demonstrate the superiority of GPST over GPT-2 with a comparable size in numerous tasks covering both language understanding and language generation. Meanwhile, GPST also significantly outperforms existing unsupervised SLMs on left-to-right grammar induction, while holding a substantial acceleration on training.

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="2403.08293")

Code

Syntology Ran 4 of 7 code samples harvested from 2 repositories linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 2 ran; community (archive-listed): 4 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.

ant-research/structuredlm_rtdt officialmentioned in papermentioned on GitHubpytorch report
alipay/StructuredLM_RTDT mentioned on GitHubpytorchApache-2.0 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

7 samples harvested; 4 ran; 0 honoured the contract we drafted; 3 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 · our draft was wrong
3ran
3unverified

Licence: 0 of the 7 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; each sample names its own and says which. “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.

GenerativeR2D2 ant-research/structuredlm_rtdt/model/generative_r2d2.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a784d2110f131468 · report
R2D2GenOutput ant-research/structuredlm_rtdt/model/generative_r2d2.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 1e812e0a70ef2d48 · report
load_model ant-research/structuredlm_rtdt/model/generative_r2d2.py official repository unverified Apache-2.0 (permissive) · 68f9327845ca9499 · report
reshape_for_broadcast alipay/StructuredLM_RTDT/model/Llama_flash_attn.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · f170e96bed9e0da5 · report
rotate_half alipay/StructuredLM_RTDT/model/Llama_flash_attn.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · e03d53ba9d4f9ae5 · report
apply_rotary_emb alipay/StructuredLM_RTDT/model/Llama_flash_attn.py community (archive-listed) unverified Apache-2.0 (permissive) · a1ac0c11d14eec67 · report
load_tf_weights_in_gpt2 alipay/StructuredLM_RTDT/model/gpt2_flash_attn.py community (archive-listed) unverified Apache-2.0 (permissive) · 3665fea6427d655d · report

Tasks

Constituency Grammar InductionLanguage ModelingLanguage ModellingNatural Language InferenceSentenceText Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Constituency Grammar Induction PTB Diagnostic ECG Database GPST(left to right parsing) Mean F1 (WSJ) 55.2 #16 of 24 Archive leaderboard report
Natural Language Inference MultiNLI GPST(unsupervised generative syntactic LM) Matched 81.8 #43 of 67 Archive leaderboard report
Natural Language Inference MultiNLI GPST(unsupervised generative syntactic LM) Mismatched 82.0 #43 of 67 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

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPT-2Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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