SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.08426 · 2020

Investigating Pretrained Language Models for Graph-to-Text Generation

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 2 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2007.08426.json · badge: /api/ran/2007.08426.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
UKPLab/plms-graph2text canonical (classifier label)
classifier basis: census
9 ran · 3 no recorded run
FunctionStatusWhere it lives
convert_text Ran
ran on a synthesized input
UKPLab/plms-graph2text/agenda/utils_graph2text.py
code served (permissive licence) · get_code("9490bc2c5dd83c43")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import re

def convert_text(text):
    text = text.lower()
    text = ' '.join(re.split('(\\W)', text))
    text = ' '.join(text.split())
    return text

ARGS = {
    "text": "Hello, World! This is a TEST."
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
convert_text Ran
ran on a synthesized input
UKPLab/plms-graph2text/amr/utils_graph2text.py
code served (permissive licence) · get_code("3ea4bb27e2072f0b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import re

def convert_text(text):
    text = ' '.join(re.split('(\\W)', text))
    text = ' '.join(text.split())
    return text

ARGS = {
    'text': 'Hello, World! This is a test.'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
count_trainable_parameters Ran
ran, honoured the contract we drafted
UKPLab/plms-graph2text/agenda/callbacks.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from manga-uofa/fdistill, is pointer only (licence: NONE) · get_code("a3826392847cbef3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from manga-uofa/fdistill, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

eval_bleu_sents Ran
ran on a synthesized input
UKPLab/plms-graph2text/amr/utils_graph2text.py
code served (permissive licence) · get_code("99630a47929b50fd")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile

# Create temporary files for reference and predictions
with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False) as ref_f:
    ref_file = ref_f.name
    ref_f.write("the cat sat on the mat\n")
    ref_f.write("hello world\n")

with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False) as pred_f:
    pred_file = pred_f.name
    pred_f.write("the cat sat on the mat\n")
    pred_f.write("hello world\n")

ARGS = {
    'ref_file': ref_file,
    'pred_file': pred_file,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
eval_bleu_sents_tok Ran
ran on a synthesized input
UKPLab/plms-graph2text/amr/utils_graph2text.py
code served (permissive licence) · get_code("bd41c2ca209d74c8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile

# Create temporary directory and files for the function to work with
temp_dir = tempfile.mkdtemp()

# Create a dummy prediction file with some text
pred_file = os.path.join(temp_dir, 'predictions.txt')
with open(pred_file, 'w') as f:
    f.write('the quick brown fox\n')
    f.write('jumps over the lazy dog\n')

# Create folder_data directory structure
folder_data = os.path.join(temp_dir, 'data')
os.makedirs(folder_data, exist_ok=True)

# Create a dummy target reference file
dataset = 'test'
target_file = os.path.join(folder_data, f'{dataset}.target.tok')
with open(target_file, 'w') as f:
    f.write('the quick brown fox\n')
    f.write('jumps over the lazy dog\n')

# Create dummy tokenizer and multi-bleu scripts in utils directory
utils_dir = os.path.join(temp_dir, 'utils')
os.makedirs(utils_dir, exist_ok=True)

# Create a dummy tokenizer.perl script
tokenizer_path = os.path.join(utils_dir, 'tokenizer.perl')
with open(tokenizer_path, 'w') as f:
    f.write('#!/usr/bin/perl\n')
    f.write('while(<STDIN>) { print $_; }\n')
os.chmod(tokenizer_path, 0o755)

# Create a dummy multi-bleu.perl script
multi_bleu_path = os.path.join(utils_dir, 'multi-bleu.perl')
with open(multi_bleu_path, 'w') as f:
    f.write('#!/usr/bin/perl\n')
    f.write('print "BLEU = 100.00, 100.0/100.0/100.0/100.0 (BP=1.000, ratio=1.000, hyp_len=10, ref_len=10)\n";\n')
os.chmod(multi_bleu_path, 0o755)

# Adjust the dir_path to point to our temp utils directory by creating a symlink/structure
# that the function will find
import sys
sys.path.insert(0, temp_dir)

ARGS = {
    'pred_file': pred_file,
    'folder_data': folder_data,
    'dataset': dataset
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_early_stopping_callback Ran
ran; our contract draft was wrong, not the code
UKPLab/plms-graph2text/agenda/callbacks.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from manga-uofa/fdistill, is pointer only (licence: NONE) · get_code("295d9fdc5ce0b054")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from manga-uofa/fdistill, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

label_smoothed_nll_loss Ran
ran on a synthesized input
UKPLab/plms-graph2text/agenda/utils.py
code served (permissive licence) · get_code("e386d3a24af4d168")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create log probabilities tensor
# Shape: (batch_size=2, vocab_size=4)
# lprobs should be log probabilities, so values between -inf and 0
lprobs = torch.log(torch.softmax(torch.randn(2, 4), dim=-1))

# Create target indices tensor
# Shape: (batch_size=2,) - indices into the vocabulary
# Values should be in range [0, vocab_size) or ignore_index
target = torch.tensor([1, 2], dtype=torch.long)

# Epsilon for label smoothing (typically small, e.g., 0.1)
epsilon = 0.1

# Ignore index for padding tokens
ignore_index = -100

ARGS = {
    "lprobs": lprobs,
    "target": target,
    "epsilon": epsilon,
    "ignore_index": ignore_index,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
lmap Ran
ran; our contract draft was wrong, not the code
UKPLab/plms-graph2text/agenda/utils.py
code served (permissive licence) · get_code("7c43af131a6f39a6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from typing import Callable, List, Iterable

torch.manual_seed(0)

# Define a simple callable function
def square(x):
    """Simple function that squares its input"""
    return x ** 2

# Define an iterable (list of numbers)
numbers = [1, 2, 3, 4, 5]

# Construct ARGS dict
ARGS = {
    "f": square,
    "x": numbers,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
open_file Ran
ran on a synthesized input
UKPLab/plms-graph2text/amr/comp_sacrebleu.py
code served (permissive licence) · get_code("c8825db3ade9d2ec")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os

# Create a temporary file with some content
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("line one\n")
temp_file.write("  line two with spaces  \n")
temp_file.write("line three\n")
temp_file.close()

ARGS = {
    'f': temp_file.name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
eval_chrf_test_webnlg Not yet run
unverified (harvested, no recorded run)
UKPLab/plms-graph2text/agenda/utils_graph2text.py
code served (permissive licence) · get_code("16c9346aec54122b")
How it ran

no invocation recorded.

eval_meteor_test_webnlg Not yet run
unverified (harvested, no recorded run)
UKPLab/plms-graph2text/agenda/utils_graph2text.py
code served (permissive licence) · get_code("c246a8900dfb38bb")
How it ran

no invocation recorded.

get_checkpoint_callback Not yet run
unverified (harvested, no recorded run)
UKPLab/plms-graph2text/agenda/callbacks.py
code served (permissive licence) · get_code("01cc9caede179564")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 5 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
count_trainable_parameters 13 other papers
1 dated earlier, 12 later
1911.13299 (2019-11)
What's Hidden in a Randomly Weighted Neural Network?
2010.05953 (2020-10)
COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
2010.11856 (2020-10)
XOR QA: Cross-lingual Open-Retrieval Question Answering
and 10 more not named here
get_early_stopping_callback 9 other papers
9 later
2010.11856 (2020-10)
XOR QA: Cross-lingual Open-Retrieval Question Answering
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
2105.11174 (2021-05)
Retrieval Enhanced Model for Commonsense Generation
and 6 more not named here
lmap 9 other papers
9 later
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
2104.08691 (2021-04)
The Power of Scale for Parameter-Efficient Prompt Tuning
2105.04779 (2021-05)
EL-Attention: Memory Efficient Lossless Attention for Generation
and 6 more not named here
label_smoothed_nll_loss 7 other papers
7 later
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
2104.08691 (2021-04)
The Power of Scale for Parameter-Efficient Prompt Tuning
2105.04779 (2021-05)
EL-Attention: Memory Efficient Lossless Attention for Generation
and 4 more not named here
get_checkpoint_callback 1 other paper
1 later
2302.05574 (2023-02)
NapSS: Paragraph-level Medical Text Simplification via Narrative Prompting and Sentence-matching Summarization

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2007.08426")
get_code_for_paper("2007.08426")
have("2007.08426")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2007.08426.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2007.08426.svg)](https://syntology.ai/paper/2007.08426)

Connect an agent — have() is free.