SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.12472 · EMNLP · 2021

ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models

Igor Melnyk, Pierre Dognin

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2108.12472.json · badge: /api/ran/2108.12472.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
IBM/regen canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
FunctionStatusWhere it lives
check_and_add_arguments Ran
ran on a synthesized input
IBM/regen/opts.py
code served (permissive licence) · get_code("4f1c685480732b74")
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 Namespace. 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
from argparse import Namespace

# Create a minimal args object with all required attributes
args = Namespace()

# Required attributes for path construction
args.output_dir = '/tmp/test_output'
args.jid = 5

# Required attributes for validation checks
args.num_workers = 4

# Required attributes for prepare validation
args.prepare = 'other'  # Not the problematic 'webnlg-lex1-kbpm'
args.prepare_permutation = 'internal'

# Required attributes for SCST validation - set to False to skip that branch
args.scst = False

# Even though scst is False, we may want to test with it enabled
# So let's create a version that tests the SCST path
args_scst = Namespace()
args_scst.output_dir = '/tmp/test_output'
args_scst.jid = 3
args_scst.num_workers = 2
args_scst.prepare = 'other'
args_scst.prepare_permutation = 'internal'
args_scst.scst = True
args_scst.scst_metrics = 'sacre_bleu:0.5,bleu_nltk:0.5'
args_scst.src = 'B'

# Test with different metric combinations
args_scst_single = Namespace()
args_scst_single.output_dir = '/tmp/test_output2'
args_scst_single.jid = 1
args_scst_single.num_workers = 1
args_scst_single.prepare = 'other'
args_scst_single.prepare_permutation = 'internal'
args_scst_single.scst = True
args_scst_single.scst_metrics = 'exactF1:1.0'
args_scst_single.src = 'A'

# Use the basic non-SCST version as the main test case
ARGS = {
    'args': args
}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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

Automatic construction of relevant Knowledge Bases (KBs) from text, and generation of semantically meaningful text from KBs are both long-standing goals in Machine Learning. In this paper, we present ReGen, a bidirectional generation of text and graph leveraging Reinforcement Learning (RL) to improve performance. Graph linearization enables us to re-frame both tasks as a sequence to sequence generation problem regardless of the generative direction, which in turn allows the use of Reinforcement Learning for sequence training where the model itself is employed as its own critic leading to Self-Critical Sequence Training (SCST). We present an extensive investigation demonstrating that the use of RL via SCST benefits graph and text generation on WebNLG+ 2020 and TEKGEN datasets. Our system provides state-of-the-art results on WebNLG+ 2020 by significantly improving upon published results from the WebNLG 2020+ Challenge for both text-to-graph and graph-to-text generation tasks. More details in https://github.com/IBM/regen.

For agents

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

get_harvested_code_for_paper("2108.12472")
get_code_for_paper("2108.12472")
have("2108.12472")

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

curl https://syntology.ai/api/ran/2108.12472.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.12472.svg)](https://syntology.ai/paper/2108.12472)

Connect an agent — have() is free.