SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.01250 · 2019

Boosting Entity Linking Performance by Leveraging Unlabeled Documents

arXiv · PDF · Open in the Atlas

Code that ran

3 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 3 have no contract verdict; 0 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/1906.01250.json · badge: /api/ran/1906.01250.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
lephong/wnel canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
find_leaves Ran
ran on a synthesized input
lephong/wnel/nel/extract_ent2cat.py
code served (permissive licence) · get_code("8b57b46d448ab02c")
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 torch
import numpy as np

# The function find_leaves takes a list of nodes (dicts)
# Each node dict must have a 'route' key with a string value
# The function sorts by route and filters based on route prefixes

nodes = [
    {'route': 'a'},
    {'route': 'a/b'},
    {'route': 'a/b/c'},
    {'route': 'd'},
    {'route': 'd/e'},
    {'route': 'f'},
]

ARGS = {
    'nodes': nodes
}
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 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
load_person_names Ran
ran on a synthesized input
lephong/wnel/nel/dataset.py
code served (permissive licence) · get_code("aa74ecd862f46c82")
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 set. 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 tempfile
import os

# Create a temporary file with person names
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "names.txt")

with open(temp_file, 'w', encoding='utf8') as f:
    f.write("John Doe\n")
    f.write("Jane Smith\n")
    f.write("Bob Johnson\n")
    f.write("Alice Williams\n")

ARGS = {
    "path": temp_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 set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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_ent_net Ran
ran on a synthesized input
lephong/wnel/nel/read_entity_network.py
code served (permissive licence) · get_code("c4a9afba6a26c7c1")
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 dict. 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 tempfile
import os

# Create a temporary directory and file for testing
temp_dir = tempfile.mkdtemp()
net_file = os.path.join(temp_dir, 'network.txt')

# Create a sample network file with the expected format
# The function expects lines with tab-separated components
# First component is ignored, subsequent components are entity names
# One component should have 'title=' in it
sample_lines = [
    'source\ttitle="Entity One"\tEntity Two\tEntity Three',
    'source\ttitle="Entity Four"\tEntity Five',
    'source\ttitle="Entity Six"\tEntity Seven\tEntity Eight\tEntity Nine',
    '',  # empty line to test len(comps) <= 1
    'source\ttitle="Entity Ten"',
]

with open(net_file, 'w') as f:
    f.write('\n'.join(sample_lines))

# Create ent2id mapping
# The function constructs wiki URLs like: en.wikipedia.org/wiki/Entity_Name
wiki_prefix = 'en.wikipedia.org/wiki/'
ent2id = {
    wiki_prefix + 'Entity_One': 0,
    wiki_prefix + 'Entity_Two': 1,
    wiki_prefix + 'Entity_Three': 2,
    wiki_prefix + 'Entity_Four': 3,
    wiki_prefix + 'Entity_Five': 4,
    wiki_prefix + 'Entity_Six': 5,
    wiki_prefix + 'Entity_Seven': 6,
    wiki_prefix + 'Entity_Eight': 7,
    wiki_prefix + 'Entity_Nine': 8,
    wiki_prefix + 'Entity_Ten': 9,
}

# Create exclude set (entities to exclude from the network)
exclude = {5}  # Exclude Entity Six (id 5)

ARGS = {
    'net_path': net_file,
    'exclude': exclude,
    'ent2id': ent2id,
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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_conll_file Not yet run
unverified (harvested, no recorded run)
lephong/wnel/nel/dataset.py
code served (permissive licence) · get_code("1a2c1760ddb8df3a")
How it ran

no invocation recorded.

read_csv_file Not yet run
unverified (harvested, no recorded run)
lephong/wnel/nel/dataset.py
code served (permissive licence) · get_code("bc696571050e0978")
How it ran

no invocation recorded.

read_exlude Not yet run
unverified (harvested, no recorded run)
lephong/wnel/nel/read_entity_network.py
code served (permissive licence) · get_code("611ace9429a11414")
How it ran

no invocation recorded.

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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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
load_person_names 1 other paper
1 dated earlier
1804.10637 (2018-04)
Improving Entity Linking by Modeling Latent Relations between Mentions
read_csv_file 1 other paper
1 dated earlier
1804.10637 (2018-04)
Improving Entity Linking by Modeling Latent Relations between Mentions

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

Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and Wikipedia. Our approach consists of two stages. First, we construct a high recall list of candidate entities for each mention in an unlabeled document. Second, we use the candidate lists as weak supervision to constrain our document-level entity linking model. The model treats entities as latent variables and, when estimated on a collection of unlabelled texts, learns to choose entities relying both on local context of each mention and on coherence with other entities in the document. The resulting approach rivals fully-supervised state-of-the-art systems on standard test sets. It also approaches their performance in the very challenging setting: when tested on a test set sampled from the data used to estimate the supervised systems. By comparing to Wikipedia-only training of our model, we demonstrate that modeling unlabeled documents is beneficial.

For agents

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

get_harvested_code_for_paper("1906.01250")
get_code_for_paper("1906.01250")
have("1906.01250")

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

curl https://syntology.ai/api/ran/1906.01250.json

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

[![Syntology run record](https://syntology.ai/api/ran/1906.01250.svg)](https://syntology.ai/paper/1906.01250)

Connect an agent — have() is free.