SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.07699 · 2018

End-to-End Neural Entity Linking

arXiv · PDF · Open in the Atlas

Code that ran

1 of 9 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; 8 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/1808.07699.json · badge: /api/ran/1808.07699.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
dalab/end2end_neural_el canonical (classifier label)
classifier basis: census
1 ran · 8 no recorded run
FunctionStatusWhere it lives
print_global_pairwise_voting Ran
ran on a synthesized input
dalab/end2end_neural_el/code/evaluation/print_predictions.py
code served (permissive licence) · get_code("f1c3c0b42dad0f25")
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 numpy as np
from unittest.mock import Mock

# Create mock objects and data structures

# gmask: 2D numpy array [num_spans, num_candidates]
gmask = np.array([
    [0.0, 1.0, 0.5, 0.0],
    [1.0, 0.0, 0.8, 1.0],
    [0.0, 0.0, 0.0, 0.0],
], dtype=np.float32)

# span_num_b_e_gt: list of tuples (other_span, begin, end, gt_info)
span_num_b_e_gt = [
    (0, 0, 2, None),
    (1, 2, 4, None),
    (2, 4, 6, None),
]

# reconstructed_words: list of words
reconstructed_words = ["the", "quick", "brown", "fox", "jumps", "over"]

# cand_entities: list of lists of entity indices
cand_entities = [
    [0, 1, 2, 3],
    [1, 2, 3, 4],
    [0, 1, 2, 3],
]

# entity_embeddings: list of 2D arrays [num_candidates, embedding_dim]
entity_embeddings = [
    np.array([[1.0, 0.0, 0.5, 0.2], [0.5, 0.5, 0.0, 0.3], [0.2, 0.1, 0.8, 0.1], [0.0, 0.9, 0.2, 0.4]], dtype=np.float32),
    np.array([[0.3, 0.2, 0.1, 0.5], [0.8, 0.1, 0.2, 0.0], [0.1, 0.7, 0.3, 0.2], [0.6, 0.0, 0.5, 0.1]], dtype=np.float32),
    np.array([[0.5, 0.5, 0.0, 0.5], [0.2, 0.3, 0.7, 0.1], [0.4, 0.2, 0.2, 0.6], [0.1, 0.1, 0.1, 0.8]], dtype=np.float32),
]

# printPredictions: mock object with map_entity method
printPredictions = Mock()
printPredictions.map_entity = Mock(side_effect=lambda ent_id, onlyname=False: f"Entity{ent_id}")

# span_num: integer index of current span
span_num = 1

# winner_pos: integer index of winner candidate
winner_pos = 0

# gt_pos: integer index of ground truth candidate
gt_pos = 1

ARGS = {
    "gmask": gmask,
    "span_num_b_e_gt": span_num_b_e_gt,
    "reconstructed_words": reconstructed_words,
    "cand_entities": cand_entities,
    "printPredictions": printPredictions,
    "entity_embeddings": entity_embeddings,
    "span_num": span_num,
    "winner_pos": winner_pos,
    "gt_pos": gt_pos,
}
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 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_records_of_one_epoch Not yet run
unverified (harvested, no recorded run)
dalab/end2end_neural_el/code/model/reader.py
code served (permissive licence) · get_code("cf2ac6212c109bad")
How it ran

no invocation recorded.

ffnn Not yet run
unverified (harvested, no recorded run)
dalab/end2end_neural_el/code/model/util.py
code served (permissive licence) · get_code("2783623121f34ed6")
How it ran

no invocation recorded.

parse_sequence_example Not yet run
unverified (harvested, no recorded run)
dalab/end2end_neural_el/code/model/reader.py
code served (permissive licence) · get_code("f30aba7c2f15ac0a")
How it ran

no invocation recorded.

print_thr_and_ffnn_values Not yet run
unverified (harvested, no recorded run)
dalab/end2end_neural_el/code/model/evaluate.py
code served (permissive licence) · get_code("a53038ea118bb28b")
How it ran

no invocation recorded.

projection Not yet run
unverified (harvested, no recorded run)
dalab/end2end_neural_el/code/model/util.py
code served (permissive licence) · get_code("cc4b9136dc71723e")
How it ran

no invocation recorded.

shape Not yet run
unverified (harvested, no recorded run)
dalab/end2end_neural_el/code/model/util.py
code served (permissive licence) · get_code("6cba6c8288c8fc1c")
How it ran

no invocation recorded.

threshold_calculation Not yet run
unverified (harvested, no recorded run)
dalab/end2end_neural_el/code/evaluation/metrics.py
code served (permissive licence) · get_code("a7a26309df5ddd6e")
How it ran

no invocation recorded.

train_input_pipeline Not yet run
unverified (harvested, no recorded run)
dalab/end2end_neural_el/code/model/reader.py
code served (permissive licence) · get_code("333009d3e4f6d78e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

Entity Linking (EL) is an essential task for semantic text understanding and information extraction. Popular methods separately address the Mention Detection (MD) and Entity Disambiguation (ED) stages of EL, without leveraging their mutual dependency. We here propose the first neural end-to-end EL system that jointly discovers and links entities in a text document. The main idea is to consider all possible spans as potential mentions and learn contextual similarity scores over their entity candidates that are useful for both MD and ED decisions. Key components are context-aware mention embeddings, entity embeddings and a probabilistic mention - entity map, without demanding other engineered features. Empirically, we show that our end-to-end method significantly outperforms popular systems on the Gerbil platform when enough training data is available. Conversely, if testing datasets follow different annotation conventions compared to the training set (e.g. queries/ tweets vs news documents), our ED model coupled with a traditional NER system offers the best or second best EL accuracy.

For agents

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

get_harvested_code_for_paper("1808.07699")
get_code_for_paper("1808.07699")
have("1808.07699")

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

curl https://syntology.ai/api/ran/1808.07699.json

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

[![Syntology run record](https://syntology.ai/api/ran/1808.07699.svg)](https://syntology.ai/paper/1808.07699)

Connect an agent — have() is free.