SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.04223 · ICLR · 2021

Workshop on Deep Learning on Graphs for Natural Language Processing KELM: KNOWLEDGE ENHANCED PRE-TRAINED LAN-GUAGE REPRESENTATIONS WITH MESSAGE PASSING ON HIERARCHICAL RELATIONAL GRAPHS

Qun Liu, Yinquan Lu, Haonan Lu, Guirong Fu

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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 5 have no contract verdict; 1 failure of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2109.04223.json · badge: /api/ran/2109.04223.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
nlp-anonymous-happy/anonymous-kg-guided-nlp canonical (classifier label)
classifier basis: plan_row
6 ran · 0 no recorded run
FunctionStatusWhere it lives
to_list Ran
ran; our contract draft was wrong, not the code
nlp-anonymous-happy/anonymous-kg-guided-nlp/src/run_copa.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from AI-secure/InfoBERT, is pointer only (licence: NONE) · get_code("9df40357afea56cc")
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 AI-secure/InfoBERT, 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.

configure_tokenizer_model_bert Ran
ran on a synthesized input
nlp-anonymous-happy/anonymous-kg-guided-nlp/src/model/bert.py
code served (permissive licence) · get_code("881ea8793bf870d1")
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 logging
from unittest.mock import Mock, MagicMock
import torch

# Create a mock logger
logger = logging.getLogger(__name__)
logger.setLevel(logging.INFO)
handler = logging.StreamHandler()
logger.addHandler(handler)

# Create a mock tokenizer with vocab attribute
mock_tokenizer = Mock()
mock_tokenizer.vocab = {'[PAD]': 0, '[UNK]': 1, '[CLS]': 2, '[SEP]': 3, 'the': 4, 'test': 5}

# Create a mock BertConfig
mock_config = Mock()
mock_config.vocab_size = 6
mock_config.hidden_size = 768
mock_config.num_hidden_layers = 12

# Create a mock model (AutoModel or BertForQuestionAnswering)
mock_model = Mock()
mock_model.config = mock_config

# Create args object with all required attributes
args = Mock()
args.config_name = None
args.model_name_or_path = "bert-base-uncased"
args.do_lower_case = True
args.init_dir = "/tmp/bert_cache"

# Mock the from_pretrained methods to return our mocks
import transformers
transformers.BertTokenizer.from_pretrained = Mock(return_value=mock_tokenizer)
transformers.BertConfig.from_pretrained = Mock(return_value=mock_config)
transformers.AutoModel.from_pretrained = Mock(return_value=mock_model)
transformers.BertForQuestionAnswering.from_pretrained = Mock(return_value=mock_model)

ARGS = {
    "args": args,
    "logger": logger,
    "is_preprocess": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — 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
preprocess_nell_ent_name Ran
ran on a synthesized input
nlp-anonymous-happy/anonymous-kg-guided-nlp/src/kgs_retrieve/nell.py
code served (permissive licence) · get_code("88f0e09ed13a1e65")
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 string

def preprocess_nell_ent_name(raw_name):
    ent_name = raw_name.split(':')[-1]
    digits = set(string.digits)
    if ent_name.startswith('n') and all([char in digits for char in ent_name.split('_')[0][1:]]):
        ent_name = ent_name[1:]
    ent_name = '_'.join(filter(lambda x: len(x) > 0, ent_name.split('_')))
    return ent_name

# Test case 1: Simple entity name without namespace prefix
ARGS = {
    "raw_name": "concept:person_john"
}
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
preprocess_record_ent_name Ran
ran on a synthesized input
nlp-anonymous-happy/anonymous-kg-guided-nlp/src/kgs_retrieve/nell.py
code served (permissive licence) · get_code("2ea3a5a500562286")
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 string

puncs = set(string.punctuation)

def preprocess_record_ent_name(raw_str):
    raw_str.replace(' ', '_')
    raw_str = ''.join((c for c in raw_str if c == '_' or c not in puncs))
    return raw_str

ARGS = {
    'raw_str': 'hello world! this-is_a test@123'
}
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
read_concept_embedding Ran
ran on a synthesized input
nlp-anonymous-happy/anonymous-kg-guided-nlp/src/kgs_retrieve/baseretriever.py
code served (permissive licence) · get_code("e97ed6b90bab1416")
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. 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 numpy as np
import tempfile
import os

# Create a temporary embedding file
temp_dir = tempfile.mkdtemp()
embedding_path = os.path.join(temp_dir, "test_embeddings.txt")

# Write test embedding data
with open(embedding_path, 'w', encoding='utf-8') as f:
    f.write("concept1 0.1 0.2 0.3 0.4\n")
    f.write("concept2 0.5 0.6 0.7 0.8\n")
    f.write("concept3 0.9 1.0 1.1 1.2\n")

ARGS = {
    "embedding_path": embedding_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
run_strip_accents Ran
ran on a synthesized input
nlp-anonymous-happy/anonymous-kg-guided-nlp/src/kgs_retrieve/baseretriever.py
code served (permissive licence) · get_code("5efae5d998e8fd45")
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 unicodedata

def run_strip_accents(text):
    """Strips accents from a piece of text."""
    text = unicodedata.normalize('NFD', text)
    output = []
    for char in text:
        cat = unicodedata.category(char)
        if cat == 'Mn':
            continue
        output.append(char)
    return ''.join(output)


# Setup code to construct valid arguments
ARGS = {
    'text': 'café naïve résumé'
}
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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 5 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
to_list 41 other papers
20 dated earlier, 3 the same month, 15 later, 3 same year, order not determinable
1902.01718 (2019-02)
End-to-End Open-Domain Question Answering with BERTserini
1910.06188 (2019-10)
Q8BERT: Quantized 8Bit BERT
1911.02984 (2019-11)
The TechQA Dataset
and 38 more not named here

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

Incorporating factual knowledge into pre-trained language models (PLM) such as BERT is an emerging trend in recent NLP studies. However, most of the existing methods combine the external knowledge integration module with a modified pre-training loss and re-implement the pre-training process on the large-scale corpus. Re-pretraining these models is usually resource-consuming, and difficult to adapt to another domain with a different knowledge graph (KG). Besides, those works either cannot embed knowledge context dynamically according to textual context or struggle with the knowledge ambiguity issue. In this paper, we propose a novel knowledge-aware language model framework based on fine-tuning process, which equips PLM with a unified knowledge-enhanced text graph that contains both text and multi-relational sub-graphs extracted from KG. We design a hierarchical relational-graph-based message passing mechanism, which allows the representations of injected KG and text to mutually update each other and can dynamically select ambiguous mentioned entities that share the same text 1 . Our empirical results show that our model can efficiently incorporate world knowledge from KGs into existing language models such as BERT, and achieve significant improvement on the machine reading comprehension (MRC) tasks compared with other knowledge-enhanced models.

For agents

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

get_harvested_code_for_paper("2109.04223")
get_code_for_paper("2109.04223")
have("2109.04223")

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

curl https://syntology.ai/api/ran/2109.04223.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.04223.svg)](https://syntology.ai/paper/2109.04223)

Connect an agent — have() is free.