Papers › Data-to-text Generation by Splicing Together Nearest Neighbors

Data-to-text Generation by Splicing Together Nearest Neighbors

20 Jan 2021EMNLP 2021 11arXiv:2101.08248archive 2025-07-28

Sam Wiseman, Arturs Backurs, Karl Stratos

We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from "neighbor" source-target pairs. Unlike recent work that conditions on retrieved neighbors but generates text token-by-token, left-to-right, we learn a policy that directly manipulates segments of neighbor text, by inserting or replacing them in partially constructed generations. Standard techniques for training such a policy require an oracle derivation for each generation, and we prove that finding the shortest such derivation can be reduced to parsing under a particular weighted context-free grammar. We find that policies learned in this way perform on par with strong baselines in terms of automatic and human evaluation, but allow for more interpretable and controllable generation.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 10 code samples harvested from 1 repository linked to this paper: 9 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 9 ran (3 with no instrument failure; 6 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

swiseman/neighbor-splicing officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 9 ran (6 instrument-failed) · 1 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

10 samples harvested: 9 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 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.

2ran · honoured contract
2ran · our draft was wrong
4ran; the contract check could not run
1ran
1unverified

Licence: 10 of the 10 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 swiseman/neighbor-splicing. “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.

swiseman/neighbor-splicing official repository 10 samples, 9 ran (6 instrument-failed) · 1 unverified
Hyp se_search.py ran no licence file found · pointer only · dcb4455b9661f0c9 · report fixture: returned Hyp · level recorded 2026-09-22
endidx2pred se_search.py ran · honoured contract fingerprinted no licence file found · pointer only · 3d43725ce088f540 · report fixture: signature endidx:int/0/int, max_remlen:int/0/int · returned tuple · level recorded 2026-09-22
get_endstuff se_search.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · 4be5b29079791381 · report fixture: signature netgts:list/1/tuple, endmask:Tensor/3/bool · returned Tensor · level recorded 2026-09-22
get_leftright_endstuff se_search.py ran · honoured contract no licence file found · pointer only · b5b9e6d3a4d88223 · report fixture: signature netgts:list/1/tuple, endmask:Tensor/2/bool · returned Tensor · level recorded 2026-09-22
get_trace se_search.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · a8da01659e2b62f9 · report fixture: signature moves:list/1/tuple, val_src:list/1/str, nelist:list/1/int, db:MockDB/0/? · returned list · level recorded 2026-09-22
get_updated_canvs se_search.py ran · our draft was wrong no licence file found · pointer only · a77612b337ec94d7 · report fixture: signature hyps:list/1/list, db:Database/0/?, device:str/0/str, nolengths:bool/0/bool · returned tuple · level recorded 2026-09-22
init_search se_search.py ran · our draft was wrong no licence file found · pointer only · 7589dead6d061a1f · report fixture: signature batchidxs:list/1/int, nelist:list/1/int, db:MinimalDB/0/?, nolengths:bool/0/bool · returned tuple · level recorded 2026-09-22
make_nemask se_search.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · 7281b50bbf89daa6 · report fixture: signature neighbs:Tensor/2/int, neoffs:Tensor/1/int, pad_idx:int/0/int · returned Tensor · level recorded 2026-09-22
startidx2pred se_search.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · b42f39e814ed2611 · report fixture: signature startidx:int/0/int, colpercanv:int/0/int, nelen:int/0/int, nne:int/0/int, nelist:list/1/int, db:StandInDB/0/? · returned tuple · level recorded 2026-09-22
se_search se_search.py unverified no licence file found · pointer only · 8bc22af12da5dab7 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for splicing together retrieved segments of text from neighbor source-target pairs (graph method: splicing together retrieved segments of text from neighbor source-target pairs). 10 bricks; individually on a fixture: 9 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. se_search entry · level 0 · unverified · 8bc22af12da5dab7
  2. Hyp helper · level 1 · ran · dcb4455b9661f0c9
  3. endidx2pred helper · level 1 · ran · honoured contract · 3d43725ce088f540
  4. get_endstuff helper · level 1 · ran; the contract check could not run (RAISES) · 4be5b29079791381
  5. get_leftright_endstuff helper · level 1 · ran · honoured contract · b5b9e6d3a4d88223
  6. get_updated_canvs helper · level 1 · ran · our draft was wrong · a77612b337ec94d7
  7. init_search helper · level 1 · ran · our draft was wrong · 7589dead6d061a1f
  8. make_nemask helper · level 1 · ran; the contract check could not run (RAISES) · 7281b50bbf89daa6
  9. startidx2pred helper · level 1 · ran; the contract check could not run (RAISES) · b42f39e814ed2611
  10. get_trace helper · level 1 · ran; the contract check could not run (RAISES) · a8da01659e2b62f9

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2101.08248") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Conditional Text GenerationData-to-Text GenerationText Generation

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