Papers › Sequence-to-Sequence Learning with Latent Neural Grammars

Sequence-to-Sequence Learning with Latent Neural Grammars

2 Sep 2021NeurIPS 2021 12arXiv:2109.01135archive 2025-07-28

Yoon Kim

Sequence-to-sequence learning with neural networks has become the de facto standard for sequence prediction tasks. This approach typically models the local distribution over the next word with a powerful neural network that can condition on arbitrary context. While flexible and performant, these models often require large datasets for training and can fail spectacularly on benchmarks designed to test for compositional generalization. This work explores an alternative, hierarchical approach to sequence-to-sequence learning with quasi-synchronous grammars, where each node in the target tree is transduced by a node in the source tree. Both the source and target trees are treated as latent and induced during training. We develop a neural parameterization of the grammar which enables parameter sharing over the combinatorial space of derivation rules without the need for manual feature engineering. We apply this latent neural grammar to various domains -- a diagnostic language navigation task designed to test for compositional generalization (SCAN), style transfer, and small-scale machine translation -- and find that it performs respectably compared to standard baselines.

PaperPDFConference PDFCodeCode 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 9 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); found in paper text by Syntology: 7 samples from 1 repository, 7 ran (7 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yoonkim/neural-qcfg officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

9 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 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.

1ran · honoured contract
1ran · our draft was wrong
7ran

Licence: 2 of the 9 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

yoonkim/neural-qcfg official repository 2 samples, 2 ran (1 instrument-failed) · 0 unverified
eval in 90 papers train_scan.py ran · honoured contract no licence file found · pointer only · aa6ca10cb935fd60 · report fixture: signature data:list/1/dict, encoder:callable/0/?, decoder:callable/0/?, parser:callable/0/?, device:device/0/?, x_tokenizer:StandInTokenizer/0/?, y_tokenizer:StandInTokenizer/0/? · returned float64 · level recorded 2026-09-22
get_data in 223 papers train_scan.py ran · our draft was wrong no licence file found · pointer only · 1e93c709a6443925 · report fixture: signature data_file:str/0/str · returned list · level recorded 2026-09-22
yli1/CGPS found in paper text by Syntology 7 samples, 7 ran (0 instrument-failed) · 0 unverified
clip_gradient_norms simple_model.py ran Apache-2.0 (permissive) · 7c681c304ce98b5e · report fixture: signature gradients:list/1/ResourceVariable, max_norm:float/0/float · returned list · level recorded 2026-09-25
filter in 20 papers adj_data_generator.py ran Apache-2.0 (permissive) · eebdf51e5b834f99 · report fixture: signature train:list/1/tuple, test:list/1/tuple · returned list · level recorded 2026-09-25
filter_actions attention_visualization.py ran Apache-2.0 (permissive) · 313e5178bdef7bfc · report fixture: signature actions:list/1/str · returned list · level recorded 2026-09-26
filter_words in 5 papers attention_visualization.py ran fingerprinted Apache-2.0 (permissive) · efe28f7dd3f19e7f · report fixture: signature words:list/1/str · returned list · level recorded 2026-09-26
get_data_generator data_generator.py ran Apache-2.0 (permissive) · d7a865546b1fb0ce · report fixture: signature name:str/0/str, args:FewShotArgs/0/? · returned FewShotDataGenerator · level recorded 2026-09-26
get_sample in 14 papers adj_data_generator.py ran Apache-2.0 (permissive) · ad335e7ef703cc26 · report fixture: signature TV:str/0/str, A1:str/0/str, A2:str/0/str, A3:str/0/str, N:str/0/str, L1:str/0/str, L2:str/0/str, L3:str/0/str · returned tuple · level recorded 2026-09-25
get_voc_full adj_data_generator.py ran Apache-2.0 (permissive) · 6f3676e93255b14c · report fixture: signature is_train:bool/0/bool · returned tuple · level recorded 2026-09-25

Tasks

DiagnosticFeature EngineeringMachine TranslationStyle TransferTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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