Papers › BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition

BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition

26 May 2021ACL 2021 5arXiv:2105.12848archive 2025-07-28

Yinghao Li, Pranav Shetty, Lucas Liu, Chao Zhang, Le Song

We study the problem of learning a named entity recognition (NER) tagger using noisy labels from multiple weak supervision sources. Though cheap to obtain, the labels from weak supervision sources are often incomplete, inaccurate, and contradictory, making it difficult to learn an accurate NER model. To address this challenge, we propose a conditional hidden Markov model (CHMM), which can effectively infer true labels from multi-source noisy labels in an unsupervised way. CHMM enhances the classic hidden Markov model with the contextual representation power of pre-trained language models. Specifically, CHMM learns token-wise transition and emission probabilities from the BERT embeddings of the input tokens to infer the latent true labels from noisy observations. We further refine CHMM with an alternate-training approach (CHMM-ALT). It fine-tunes a BERT-NER model with the labels inferred by CHMM, and this BERT-NER's output is regarded as an additional weak source to train the CHMM in return. Experiments on four NER benchmarks from various domains show that our method outperforms state-of-the-art weakly supervised NER models by wide margins.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 15 samples from 1 repository, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 5 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Yinghao-Li/CHMM-ALT officialmentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 7 ran (0 instrument-failed) · 8 unverified report
Yinghao-Li/Sparse-CHMM mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

20 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

10ran
10unverified

Licence: 0 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Yinghao-Li/CHMM-ALT official repository 15 samples, 7 ran (0 instrument-failed) · 8 unverified
binary_search in 9 papers data_constr/src/data.py ran Apache-2.0 (permissive) · 07c3eac7eb4ccba4 · report fixture: signature start:int/0/int, end:int/0/int, intervals:list/1/tuple · returned tuple · level recorded 2026-09-25
first_nonzero_idx data_constr/src/util.py ran fingerprinted Apache-2.0 (permissive) · 0bbaea3681a4d767 · report fixture: signature x:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-25
get_overlaps data_constr/src/data.py ran Apache-2.0 (permissive) · 93b0b65911d51415 · report fixture: signature start:int/0/int, end:int/0/int, annotations:dict/0/?, sources:list/1/str · returned list · level recorded 2026-09-25
load_conll_2003_data data_constr/src/io.py ran Apache-2.0 (permissive) · 80f211d366ececf3 · report fixture: signature file_name:str/0/str · returned list · level recorded 2026-09-25
load_src_metrics src/chmm/dataset.py ran Apache-2.0 (permissive) · f837fba980069ba0 · report fixture: signature file_path:str/0/str · returned dict · level recorded 2026-09-25
one_hot in 150 papers
census: 18 implementations from 25 papers, 10 distinct outputs across 6 buckets, one shared input per bucket
data_constr/src/util.py ran Apache-2.0 (permissive) · 94f946467c015b2d · report fixture: signature x:Tensor/2/int, n_class:int/0/int · returned Tensor · level recorded 2026-09-25
one_hot_to_string data_constr/src/util.py ran fingerprinted Apache-2.0 (permissive) · ceaaa5aea0a1ffec · report fixture: signature x:Tensor/2/float · returned list · level recorded 2026-09-25
batch_prep src/chmm/dataset.py unverified Apache-2.0 (permissive) · 796e527adb2ed3d8 · report
bc5cdr_annotators data_constr/src/wiser_annotator.py unverified Apache-2.0 (permissive) · ebe8e4be2bc36479 · report
collate_fn in 500 papers src/chmm/dataset.py unverified Apache-2.0 (permissive) · 0e2242a9ea204327 · report
construct_spacy_doc data_constr/src/skweak_annotator.py unverified Apache-2.0 (permissive) · 1513a7e3c40ee51a · report
laptop_annotators data_constr/src/wiser_annotator.py unverified Apache-2.0 (permissive) · b7f01e56a9691559 · report
load_bc5cdr_sentences data_constr/src/io.py unverified Apache-2.0 (permissive) · 4182f6dbfbb21083 · report
load_wikigold_data data_constr/src/io.py unverified Apache-2.0 (permissive) · 223f33cec8c8003d · report
ncbi_annotators data_constr/src/wiser_annotator.py unverified Apache-2.0 (permissive) · 092662782020e348 · report
Yinghao-Li/Sparse-CHMM community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
batch_prep sparse_chmm/collate.py ran Apache-2.0 (permissive) · 6a3a0bf29f78b0d6 · report fixture: signature emb_list:list/1/Tensor, obs_list:list/1/Tensor, txt_list:list/1/list, lbs_list:list/1/dict · returned tuple · level recorded 2026-09-24
log_matmul sparse_chmm/math.py ran fingerprinted Apache-2.0 (permissive) · 294c159dee8bc557 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-24
logsumexp in 55 papers
census: 8 implementations from 12 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
sparse_chmm/math.py ran Apache-2.0 (permissive) · 9b68df96cc5a0174 · report fixture: signature x:Tensor/2/float, dim:NoneType/0/?, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-24
collate_fn in 500 papers sparse_chmm/collate.py unverified Apache-2.0 (permissive) · e14737726145e981 · report
log_maxmul sparse_chmm/math.py unverified Apache-2.0 (permissive) · e89483f11a57dcbe · report

Tasks

NERNamed Entity RecognitionNamed Entity Recognition (NER)Weakly-Supervised Named Entity Recognitionnamed-entity-recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections