SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2012.10608 · EMNLP · 2020

Uncertainty-Aware Label Refinement for Sequence Labeling

Qi Zhang, Yeyun Gong, Xuanjing Huang, Jiacheng Ye, Tao Gui, Zichu Fei, Zhengyan Li

arXiv · PDF · Open in the Atlas

Code that ran

13 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (8 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 3 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/2012.10608.json · badge: /api/ran/2012.10608.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
jiacheng-ye/UANet marked official in Papers with Code
Papers with Code archive
13 ran · 5 no recorded run
FunctionStatusWhere it lives
CharBiGRU Ran
ran on a synthesized input · constructed an object; no result was computed
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("7c0d1d0c6504a6e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

CharBiLSTM Ran
ran on a synthesized input · constructed an object; no result was computed
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("a2f76e16a893290e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

CharCNN Ran
ran on a synthesized input · constructed an object; no result was computed
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("0db9f46fe3bd2988")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

RelTransformerLayer Ran
ran on a synthesized input · constructed an object; no result was computed
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("b24a7e9eb7727d1a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

RelativeMultiHeadAttn Ran
ran on a synthesized input · constructed an object; no result was computed
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("3ce598afaa4512fb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

RelativePositionalEmbedding Ran
ran on a synthesized input · constructed an object; no result was computed
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("fbcbfa1fcbcc467f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

RelativeSinusoidalPositionalEmbedding Ran
ran on a synthesized input · constructed an object; no result was computed
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("9c0fb26e71e451ec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

TwoStreamRelTransformerLayer Ran
ran on a synthesized input · constructed an object; no result was computed
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("52c59e9167b1537a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

add_dropout Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("c0e8373855face92")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

epistemic_uncertainty Ran
ran; our contract draft was wrong, not the code
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("ce80c98d271934f4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

generate_label_mask Ran
ran; our contract draft was wrong, not the code
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("5aabd066fb658aa9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

random_embedding Ran
ran, honoured the contract we drafted
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("ffcb36e0c6ef81dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

random_embedding_label Ran
ran, honoured the contract we drafted
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("715f7ee86333dc5b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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.

MCmodel Not yet run
unverified (harvested, no recorded run)
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("0b41d1b3763800d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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. No invocation recorded.

RelativeEmbedding Not yet run
unverified (harvested, no recorded run)
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("d2f1976c4a9be660")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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. No invocation recorded.

SeqModel Not yet run
unverified (harvested, no recorded run)
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("decee8984866853d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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. No invocation recorded.

TransformerEncoder Not yet run
unverified (harvested, no recorded run)
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("01afcb01278b5d15")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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. No invocation recorded.

WordRep Not yet run
unverified (harvested, no recorded run)
jiacheng-ye/UANet/model/seqmodel.py
pointer only (licence: NONE) · get_code("8cc80cc6f0356bc1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiacheng-ye/UANet 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. No invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 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 17 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
random_embedding
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later
2010.08895 (2020-10)
Fourier Neural Operator for Parametric Partial Differential Equations
2210.02724 (2022-10)
Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks. However, the local label dependencies and inefficient Viterbi decoding have always been a problem to be solved. In this work, we introduce a novel two-stage label decoding framework to model long-term label dependencies, while being much more computationally efficient. A base model first predicts draft labels, and then a novel twostream self-attention model makes refinements on these draft predictions based on longrange label dependencies, which can achieve parallel decoding for a faster prediction. In addition, in order to mitigate the side effects of incorrect draft labels, Bayesian neural networks are used to indicate the labels with a high probability of being wrong, which can greatly assist in preventing error propagation. The experimental results on three sequence labeling benchmarks demonstrated that the proposed method not only outperformed the CRF-based methods but also greatly accelerated the inference process.

For agents

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

get_harvested_code_for_paper("2012.10608")
get_code_for_paper("2012.10608")
have("2012.10608")

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

curl https://syntology.ai/api/ran/2012.10608.json

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

[![Syntology run record](https://syntology.ai/api/ran/2012.10608.svg)](https://syntology.ai/paper/2012.10608)

Connect an agent — have() is free.