Papers › Investigating Pretrained Language Models for Graph-to-Text Generation

Investigating Pretrained Language Models for Graph-to-Text Generation

16 Jul 2020EMNLP (NLP4ConvAI) 2021 11arXiv:2007.08426archive 2025-07-28

Leonardo F. R. Ribeiro, Martin Schmitt, Hinrich Schütze, Iryna Gurevych

Graph-to-text generation aims to generate fluent texts from graph-based data. In this paper, we investigate two recently proposed pretrained language models (PLMs) and analyze the impact of different task-adaptive pretraining strategies for PLMs in graph-to-text generation. We present a study across three graph domains: meaning representations, Wikipedia knowledge graphs (KGs) and scientific KGs. We show that the PLMs BART and T5 achieve new state-of-the-art results and that task-adaptive pretraining strategies improve their performance even further. In particular, we report new state-of-the-art BLEU scores of 49.72 on LDC2017T10, 59.70 on WebNLG, and 25.66 on AGENDA datasets - a relative improvement of 31.8%, 4.5%, and 42.4%, respectively. In an extensive analysis, we identify possible reasons for the PLMs' success on graph-to-text tasks. We find evidence that their knowledge about true facts helps them perform well even when the input graph representation is reduced to a simple bag of node and edge labels.

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 12 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 9 ran (9 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 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

UKPLab/plms-graph2text officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 9 ran (0 instrument-failed) · 3 unverified report
bjascob/amrlib mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AMR Parsing via Graph-Sequence Iterative Inference (arXiv:2004.05572; that paper's own run record: 21 ran (of which 11 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
ukplab/m-amr2text mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation (arXiv:2109.03808; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

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

9ran
3unverified

Licence: 2 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from UKPLab/plms-graph2text. “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.

UKPLab/plms-graph2text official repository 12 samples, 9 ran (0 instrument-failed) · 3 unverified
convert_text agenda/utils_graph2text.py ran fingerprinted Apache-2.0 (permissive) · 9490bc2c5dd83c43 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-25
convert_text amr/utils_graph2text.py ran fingerprinted Apache-2.0 (permissive) · 3ea4bb27e2072f0b · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-25
count_trainable_parameters in 21 papers agenda/callbacks.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · a3826392847cbef3 · report fixture: signature model:callable/0/? · returned int64 · level recorded 2026-09-24
eval_bleu_sents amr/utils_graph2text.py ran Apache-2.0 (permissive) · 99630a47929b50fd · report fixture: returned str · level recorded 2026-09-25
eval_bleu_sents_tok amr/utils_graph2text.py ran Apache-2.0 (permissive) · bd41c2ca209d74c8 · report fixture: returned str · level recorded 2026-09-25
get_early_stopping_callback in 12 papers agenda/callbacks.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 295d9fdc5ce0b054 · report fixture: signature metric:str/0/str, patience:int/0/int · returned EarlyStopping · level recorded 2026-09-24
label_smoothed_nll_loss in 43 papers agenda/utils.py ran Apache-2.0 (permissive) · e386d3a24af4d168 · report fixture: signature lprobs:Tensor/2/float, target:Tensor/1/int, epsilon:float/0/float, ignore_index:int/0/int · returned tuple · level recorded 2026-09-26
lmap in 15 papers agenda/utils.py ran Apache-2.0 (permissive) · 7c43af131a6f39a6 · report fixture: signature f:callable/0/?, x:list/1/int · returned list · level recorded 2026-09-25
open_file in 10 papers amr/comp_sacrebleu.py ran Apache-2.0 (permissive) · c8825db3ade9d2ec · report fixture: signature f:str/0/str · returned list · level recorded 2026-09-25
eval_chrf_test_webnlg agenda/utils_graph2text.py unverified Apache-2.0 (permissive) · 16c9346aec54122b · report
eval_meteor_test_webnlg agenda/utils_graph2text.py unverified Apache-2.0 (permissive) · c246a8900dfb38bb · report
get_checkpoint_callback in 13 papers agenda/callbacks.py unverified Apache-2.0 (permissive) · 01cc9caede179564 · report

Tasks

AMR-to-Text GenerationData-to-Text GenerationKB-to-Language GenerationKG-to-Text GenerationKnowledge GraphsQuestion GenerationText Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Data-to-Text Generation WebNLG T5-small BLEU 65.05 #9 of 20 Archive leaderboard report
Data-to-Text Generation WebNLG Full T5-large BLEU 59.70 #4 of 8 Archive leaderboard report
KG-to-Text Generation AGENDA BART-large+ STA BLEU 25.66 #1 of 6 Archive leaderboard report
KG-to-Text Generation AGENDA BART-large BLEU 23.65 #2 of 6 Archive leaderboard report
KG-to-Text Generation WebNLG (All) T5_large BLEU 59.70 #1 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (All) T5_large METEOR 44.18 #1 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (All) T5_large chrF++ 75.40 #1 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (All) BART_large BLEU 54.72 #2 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (All) BART_large METEOR 42.23 #2 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (All) BART_large chrF++ 72.29 #2 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Seen) T5_large BLEU 64.71 #1 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Seen) T5_large METEOR 45.85 #1 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Seen) T5_large chrF++ 78.29 #1 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Seen) BART_large BLEU 63.45 #2 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Seen) BART_large METEOR 45.49 #2 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Seen) BART_large chrF++ 77.57 #2 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Unseen) T5_large BLEU 53.67 #1 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Unseen) T5_large METEOR 42.26 #1 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Unseen) T5_large chrF++ 72.25 #1 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Unseen) BART_large BLEU 43.97 #2 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Unseen) BART_large METEOR 38.61 #2 of 2 Archive leaderboard report
KG-to-Text Generation WebNLG (Unseen) BART_large chrF++ 66.53 #2 of 2 Archive leaderboard report
Question Generation GrailQA-Compositional T5B BLEU 31.75 #4 of 4 Archive leaderboard report
Question Generation GrailQA-Compositional T5B FactSpotter 94.84 #4 of 4 Archive leaderboard report
Question Generation GrailQA-Compositional T5B METEOR 35.64 #4 of 4 Archive leaderboard report
Question Generation GrailQA-IID T5B BLEU 44.51 #3 of 4 Archive leaderboard report
Question Generation GrailQA-IID T5B FactSpotter 99.43 #3 of 4 Archive leaderboard report
Question Generation GrailQA-IID T5B METEOR 42.71 #3 of 4 Archive leaderboard report
Question Generation GrailQA-Zero-Shot T5B FactSpotter 94.77 #4 of 4 Archive leaderboard report
Question Generation GrailQA-Zero-Shot T5B METEOR 37.35 #4 of 4 Archive leaderboard report
Question Generation GrailQA-Zero-Shot T5B bleu 32.20 #4 of 4 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

AdafactorAdamAttentionAttention DropoutBARTBPEDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSentencePieceSoftmaxT5

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