SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.03792 · EMNLP · 2021

Highly Parallel Autoregressive Entity Linking with Discriminative Correction

Wilker Aziz, Nicola De Cao, Ivan Titov

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 2 have no contract verdict; 1 failure of our instrument; 1 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/2109.03792.json · badge: /api/ran/2109.03792.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
nicola-decao/efficient-autoregressive-EL canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
get_markdown Ran
ran on a synthesized input
nicola-decao/efficient-autoregressive-EL/src/utils.py
code served (permissive licence) · get_code("897b09255be412e5")
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

torch.manual_seed(0)

# Construct arguments for get_markdown function
# The function takes:
# - sentences: list of strings
# - entity_spans: list of lists of tuples (begin, end, href)

sentences = [
    "Albert Einstein was a physicist.",
    "Marie Curie discovered polonium and radium."
]

entity_spans = [
    [
        (0, 6, "Albert Einstein"),
        (11, 19, "Physics"),
    ],
    [
        (0, 11, "Marie Curie"),
        (23, 31, "Polonium"),
        (36, 42, "Radium"),
    ]
]

ARGS = {
    "sentences": sentences,
    "entity_spans": entity_spans,
}
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 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
label_smoothed_nll_loss Ran
ran; our contract draft was wrong, not the code
nicola-decao/efficient-autoregressive-EL/src/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from beepkh/unike, is pointer only (licence: NONE) · get_code("96b6713ff1c322ca")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from beepkh/unike, 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.

tile Ran
ran on a synthesized input
nicola-decao/efficient-autoregressive-EL/src/beam_search.py
code served (permissive licence) · get_code("88ca47687541fb04")
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 Tensor, ndim 3, dtype family float, shape (2, 12, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 a small tensor to tile
# Shape: (batch=2, feature=4, height=3)
x = torch.randn(2, 4, 3)

# Number of times to tile
count = 3

# Dimension along which to tile
dim = 1

ARGS = {
    "x": x,
    "count": count,
    "dim": dim,
}
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 Tensor, ndim 3, dtype family float, shape (2, 12, 3) — shape (2, 12, 3) as a later run recorded it
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
beam_search Not yet run
unverified (harvested, no recorded run)
nicola-decao/efficient-autoregressive-EL/src/beam_search.py
code served (permissive licence) · get_code("f8d1fe362ffd1e5e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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
label_smoothed_nll_loss 7 other papers
1 dated earlier, 6 later
2104.08164 (2021-04)
Editing Factual Knowledge in Language Models
2210.05144 (2022-10)
Mixture of Attention Heads: Selecting Attention Heads Per Token
2023.findings-emnlp.978 (2023 (year only))
Incorporating Probing Signals into Multimodal Machine Translation via Visual Question-Answering Pairs
and 4 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

shown to be effective for both Entity Disambiguation and Entity Linking (i.e., joint mention detection and disambiguation). However, the previously proposed autoregressive formulation for EL suffers from i) high computational cost due to a complex (deep) decoder, ii) non-parallelizable decoding that scales with the source sequence length, and iii) the need for training on a large amount of data. In this work, we propose a very efficient approach that parallelizes autoregressive linking across all potential mentions and relies on a shallow and efficient decoder. Moreover, we augment the generative objective with an extra discriminative component, i.e. a correction term which lets us directly optimize the generator's ranking. When taken together, these techniques tackle all the above issues: our model is >70 times faster and more accurate than the previous generative method, outperforming stateof-the-art approaches on the standard English dataset AIDA-CoNLL. 1

For agents

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

get_harvested_code_for_paper("2109.03792")
get_code_for_paper("2109.03792")
have("2109.03792")

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

curl https://syntology.ai/api/ran/2109.03792.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.03792.svg)](https://syntology.ai/paper/2109.03792)

Connect an agent — have() is free.