Papers › Neural Architectures for Named Entity Recognition

Neural Architectures for Named Entity Recognition

4 Mar 2016NAACL 2016 6arXiv:1603.01360archive 2025-07-28

Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, Chris Dyer

State-of-the-art named entity recognition systems rely heavily on hand-crafted features and domain-specific knowledge in order to learn effectively from the small, supervised training corpora that are available. In this paper, we introduce two new neural architectures---one based on bidirectional LSTMs and conditional random fields, and the other that constructs and labels segments using a transition-based approach inspired by shift-reduce parsers. Our models rely on two sources of information about words: character-based word representations learned from the supervised corpus and unsupervised word representations learned from unannotated corpora. Our models obtain state-of-the-art performance in NER in four languages without resorting to any language-specific knowledge or resources such as gazetteers.

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

The archive's official repositories (clab/stack-lstm-ner, glample/tagger) were not harvested; the 36 samples below come from 15 community repositories.

Syntology 36 code samples harvested from 15 repositories linked to this paper: 29 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 1 violated, 19 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 36 samples from 15 repositories, 29 ran (22 with no instrument failure; 7 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

43 repositories listed; official and paper-mentioned ones first.

clab/stack-lstm-ner officialmentioned in papermentioned on GitHubSyntology: not harvested report
glample/tagger officialmentioned in papermentioned on GitHubApache-2.0Syntology: not harvested report
Akshayanti/supersense-sequence-labelling mentioned on GitHubSyntology: not harvested report
Coda-s/BJTU_NLP_Practice mentioned on GitHubpytorchSyntology: not harvested report
Hironsan/anago mentioned on GitHubSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
HuihuiChyan/BJTUNLP_Practice2020 mentioned on GitHubpytorchSyntology: not harvested report
HuihuiChyan/BJTUNLP_Practice2021 mentioned on GitHubpytorchSyntology: not harvested report
IBM/MAX-Named-Entity-Tagger mentioned on GitHubtfApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
IsabelMeraner/BotanicalNER mentioned on GitHubGPL-3.0Syntology: not harvested report
JZ-LIANG/CRF-LSTM-NER mentioned on GitHubtfSyntology: not harvested report
PKU-TANGENT/nlp-tutorial mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
SaeedNajafi/ac-tagger mentioned on GitHubpytorchMITSyntology: not harvested report
SuphanutN/Thai-NER-BiLSTM-WordCharEmbedding mentioned on GitHubSyntology: not harvested report
SuphanutN/Thai-NER-BiLSTMCRF-WordCharEmbedding mentioned on GitHubSyntology: not harvested report
UcasLzz/ChineseWordSeg-POS mentioned on GitHubApache-2.0Syntology: not harvested report
achernodub/targer mentioned on GitHubpytorchSyntology: not harvested report
alexerdmann/Herodotos-Project-Latin-NER-Tagger-Annotation mentioned on GitHubAGPL-3.0Syntology: not harvested report
autoih/runtime_ner mentioned on GitHubtfApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
aymara/lima-tfner mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
brendanxwhitaker/tagger-v mentioned on GitHubSyntology: not harvested report
davidalbertonogueira/NLP-tutorials mentioned on GitHubpytorchSyntology: not harvested report
deepmipt/DeepPavlov mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hybrid Code Networks: practical and efficient end-to-end dialog control with... (arXiv:1702.03274; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
deepmipt/ner mentioned on GitHubtfApache-2.0Syntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
devkotasabin/EBM-NLP mentioned on GitHubSyntology: not harvested report
flairNLP/flair mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
gitzgk/nlp-beginner mentioned on GitHubtfSyntology: not harvested report
guillaumegenthial/sequence_tagging mentioned on GitHubtfApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
guillaumegenthial/tf_ner mentioned on GitHubtfApache-2.0Syntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
herodotos-project/herodotos-project-latin-ner-tagger-annotation mentioned on GitHubAGPL-3.0Syntology: not harvested report
karlstratos/mention2vec mentioned on GitHubSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
luopeixiang/named_entity_recognition mentioned on GitHubpytorchSyntology: not harvested report
marekrei/sequence-labeler mentioned on GitHubtfSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
maviccprp/ger_ner_evals mentioned on GitHubSyntology: not harvested report
riedlma/sequence_tagging mentioned on GitHubtfApache-2.0Syntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
samueljamesbell/sequence-labeler mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
tahoora/BiLSTM-CRF mentioned on GitHubApache-2.0Syntology: not harvested report
thukg/query-entity-recognition mentioned on GitHubMITSyntology: not harvested report
vunb/anago-tagger mentioned on GitHubMITSyntology: 3 samples, 0 ran · 3 unverified report
wzzzd/LM_NER mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805; that paper's own run record: 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified) and RoBERTa: A Robustly Optimized BERT Pretraining Approach (arXiv:1907.11692; that paper's own run record: 37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
yyHaker/NamedEntityRecognition mentioned on GitHubtfSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
zjy-ucas/ChineseNER mentioned on GitHubtfSyntology: not harvested report
zysite/post mentioned on GitHubpytorchMITSyntology: not harvested report
ZubinGou/NER-BiLSTM-CRF-PyTorch pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

36 samples harvested: 29 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 1 violated, 19 with no contract checked; 7 where Syntology's instrument failed) · 7 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.

2ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
1ran; the contract check could not run
19ran
7unverified

Licence: 6 of the 36 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 15 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.

Hironsan/anago community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
filter_embeddings anago/utils.py ran · our draft was wrong MIT (permissive) · 2cbf9d02fc7275e8 · report fixture: signature embeddings:dict/0/?, vocab:dict/0/?, dim:int/0/int · returned ndarray · level recorded 2026-09-22
load_data_and_labels anago/utils.py ran · our draft was wrong MIT (permissive) · 541693fb200297a7 · report fixture: signature filename:str/0/str, encoding:str/0/str · returned tuple · level recorded 2026-09-22
IBM/MAX-Named-Entity-Tagger community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
get_processing_word core/utils.py ran Apache-2.0 (permissive) · f9c3ecd4c9aa6833 · report fixture: signature vocab_words:dict/0/?, vocab_chars:dict/0/?, lowercase:bool/0/bool, chars:bool/0/bool, allow_unk:bool/0/bool · returned function · level recorded 2026-09-26
load_vocab in 107 papers core/utils.py ran Apache-2.0 (permissive) · a0562f49c954c62c · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-26
pad_sequences in 19 papers core/utils.py ran Apache-2.0 (permissive) · 57efe0447a3a3ab6 · report fixture: signature sequences:list/1/list, pad_tok:int/0/int, nlevels:int/0/int · returned tuple · level recorded 2026-09-26
PKU-TANGENT/nlp-tutorial community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
build_vocab in 36 papers ChineseNER/preprocess_data.py ran MIT (permissive) · dd8a923e22406d00 · report fixture: signature config:Config/0/? · returned tuple · level recorded 2026-09-26
collate_fn in 500 papers ChineseNER/utils.py ran MIT (permissive) · d32e7d27376cb204 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-26
autoih/runtime_ner community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
extract_tokens api/predict.py ran Apache-2.0 (permissive) · 4cedf40326fbff61 · report fixture: signature csv_file:str/0/str · returned list · level recorded 2026-09-26
peak_memory api/mem_util.py ran Apache-2.0 (permissive) · e514cb73330d43e5 · report fixture: signature run_metadata:RunMetadata/0/? · returned dict · level recorded 2026-09-26
aymara/lima-tfner community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
align_data evaluate.py ran · our draft was wrong Apache-2.0 (permissive) · 2e30815d7869e90d · report fixture: signature data:dict/0/? · returned dict · level recorded 2026-09-22
deepmipt/ner community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
chunk_finder ner/evaluation.py ran Apache-2.0 (permissive) · 65ae5d1c944b2714 · report fixture: signature current_token:str/0/str, previous_token:str/0/str, tag:str/0/str · returned tuple · level recorded 2026-09-25
is_end_of_sentence ner/utils.py ran fingerprinted Apache-2.0 (permissive) · aff994b4180ca0f6 · report fixture: signature prev_token:str/0/str, current_token:str/0/str · returned bool · level recorded 2026-09-25
precision_recall_f1 ner/evaluation.py ran Apache-2.0 (permissive) · 6481b2ee4c62c0ba · report fixture: signature y_true:list/1/str, y_pred:list/1/str, print_results:bool/0/bool, short_report:bool/0/bool, entity_of_interest:NoneType/0/? · returned OrderedDict · level recorded 2026-09-25
stacked_rnn ner/layers.py unverified Apache-2.0 (permissive) · 4e47f6f283743daa · report
guillaumegenthial/sequence_tagging community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
get_char_vocab model/data_utils.py ran Apache-2.0 (permissive) · d8fcea9be53400c5 · report fixture: signature dataset:list/1/tuple · returned set · level recorded 2026-09-26
get_glove_vocab model/data_utils.py ran Apache-2.0 (permissive) · 05efd5b7ae13cf0c · report fixture: signature filename:str/0/str · returned set · level recorded 2026-09-26
get_logger in 383 papers model/general_utils.py ran Apache-2.0 (permissive) · 75ed1ef1f8c3d22b · report fixture: signature filename:str/0/str · returned Logger · level recorded 2026-09-25
get_vocabs in 5 papers model/data_utils.py ran Apache-2.0 (permissive) · 384baa37e7d09ae3 · report fixture: signature datasets:list/1/SimpleDataset · returned tuple · level recorded 2026-09-25
guillaumegenthial/tf_ner community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
parse_fn in 5 papers models/chars_conv_lstm_crf/serve.py ran fingerprinted Apache-2.0 (permissive) · de2e9c6541708aa6 · report fixture: signature line:str/0/str · returned dict · level recorded 2026-09-26
predict_input_fn models/chars_conv_lstm_crf/interact.py ran Apache-2.0 (permissive) · 40a3f270c3650e14 · report fixture: signature line:str/0/str · returned tuple · level recorded 2026-09-26
masked_conv1d_and_max models/chars_conv_lstm_crf/masked_conv.py unverified Apache-2.0 (permissive) · db78ae8b86c8f609 · report
karlstratos/mention2vec community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
read_embeddings display_nearest_neighbors.py ran · our draft was wrong Apache-2.0 (permissive) · 3d1adae4e91a62b3 · report fixture: signature embedding_path:str/0/str · returned tuple · level recorded 2026-09-22
marekrei/sequence-labeler community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
is_float in 14 papers experiment.py ran · violated contract fingerprinted no licence file found · pointer only · 0a315a31212d041f · report fixture: signature value:float/0/float · returned bool · level recorded 2026-09-22
read_input_files experiment.py ran · our draft was wrong no licence file found · pointer only · be54407c183e294b · report fixture: signature file_paths:str/0/str, max_sentence_length:int/0/int · returned list · level recorded 2026-09-22
parse_config in 30 papers experiment.py unverified no licence file found · pointer only · e81267fcf798eeaa · report
riedlma/sequence_tagging community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
conv in 178 papers transfer_learning.py ran Apache-2.0 (permissive) · 48c533147efe494a · report fixture: signature n:bytes/0/? · returned str · level recorded 2026-09-26
get_vocab in 15 papers model/data_utils.py ran Apache-2.0 (permissive) · 85e5be88dbd9ad46 · report fixture: signature filename:str/0/str · returned set · level recorded 2026-09-26
get_vocabs in 5 papers model/data_utils.py ran Apache-2.0 (permissive) · 3a2be4774b779b43 · report fixture: signature datasets:list/1/SimpleDataset · returned tuple · level recorded 2026-09-26
readResults transfer_learning.py unverified Apache-2.0 (permissive) · 2334e2e11796f5a6 · report
samueljamesbell/sequence-labeler community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
load_sentence_id experiment.py ran · honoured contract no licence file found · pointer only · 3cb2bb18d24e858e · report fixture: signature path:str/0/str, sentence_id:int/0/int, num_features:int/0/int, num_vectors:int/0/int · returned ndarray · level recorded 2026-09-22
vunb/anago-tagger community (archive-listed) 3 samples, 0 ran · 3 unverified
path_energy anago/layers.py unverified MIT (permissive) · 6f5b259e1a881655 · report
path_energy0 anago/layers.py unverified MIT (permissive) · e13517b914ec8cfe · report
sparse_chain_crf_loss anago/layers.py unverified MIT (permissive) · 1ba390350088f072 · report
yyHaker/NamedEntityRecognition community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
gather_index src/LSTM-CNNs-CRF/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · ebd40f0b98a8f2a4 · report fixture: signature input:Tensor/2/float, index:Tensor/1/int · returned Tensor · level recorded 2026-09-22
log_sum_exp in 51 papers
census: 10 implementations from 12 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32
src/LSTM-CNNs-CRF/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · ca4d0de367bcc625 · report fixture: signature input:Tensor/2/float, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-22
ZubinGou/NER-BiLSTM-CRF-PyTorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
log_sum_exp in 51 papers
census: 10 implementations from 12 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32
src/model.py ran · honoured contract fingerprinted MIT (permissive) · d4329236872658c9 · report fixture: signature smat:Tensor/2/float · returned Tensor · level recorded 2026-09-22

Tasks

Named Entity RecognitionNamed Entity Recognition (NER)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Named Entity Recognition (NER) CoNLL 2003 (English) LSTM-CRF F1 90.94 #70 of 73 Archive leaderboard report
Named Entity Recognition (NER) CoNLL++ LSTM-CRF F1 91.47 #11 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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