Papers › End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

4 Mar 2016ACL 2016 8arXiv:1603.01354archive 2025-07-28

Xuezhe Ma, Eduard Hovy

State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing. In this paper, we introduce a novel neutral network architecture that benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM, CNN and CRF. Our system is truly end-to-end, requiring no feature engineering or data pre-processing, thus making it applicable to a wide range of sequence labeling tasks. We evaluate our system on two data sets for two sequence labeling tasks --- Penn Treebank WSJ corpus for part-of-speech (POS) tagging and CoNLL 2003 corpus for named entity recognition (NER). We obtain state-of-the-art performance on both the two data --- 97.55\% accuracy for POS tagging and 91.21\% F1 for NER.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1603.01354")

Code

Syntology Ran 4 of 24 code samples harvested from 5 repositories linked to this paper; 20 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · our draft was wrong.

By repository: community (archive-listed): 23 samples from 5 repositories, 3 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

IBM/MAX-Named-Entity-Tagger mentioned on GitHubtfApache-2.0 report
SNUDerek/multiLSTM mentioned on GitHubtf report
SenticNet/aspect-extraction mentioned on GitHubtfApache-2.0 report
XiafeiYu/CNN_BILSTM_CRF mentioned on GitHubtf report
achernodub/targer mentioned on GitHubpytorch report
akurniawan/pytorch-sequence-tagger mentioned on GitHubpytorch report
aonotas/deep-crf mentioned on GitHubMIT report
autoih/runtime_ner mentioned on GitHubtfApache-2.0 report
aymara/lima-tfner mentioned on GitHubtf report
bestend/tf2-bi-lstm-crf-nni mentioned on GitHubtfMIT report
epwalsh/pytorch-crf mentioned on GitHubpytorchMIT report
gitzgk/nlp-beginner mentioned on GitHubtf report
gpandu/NER_DNN mentioned on GitHub report
guillaumegenthial/sequence_tagging mentioned on GitHubtfApache-2.0 report
guillaumegenthial/tf_ner mentioned on GitHubtfApache-2.0 report
monologg/korean-ner-pytorch mentioned on GitHubpytorchApache-2.0 report
riedlma/sequence_tagging mentioned on GitHubtfApache-2.0 report
soujanyaporia/aspect-extraction mentioned on GitHubtfApache-2.0 report
uahmad235/NER-Deep-Learning mentioned on GitHub 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

24 samples harvested; 4 ran; 2 honoured the contract we drafted; 20 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
20unverified

Licence: 3 of the 24 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 5 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

align_data SenticNet/aspect-extraction/evaluate.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 2e30815d7869e90d · report
leverage_embeddings uahmad235/NER-Deep-Learning/src/model.py community (archive-listed) ran · honoured contract no licence file found · pointer only · bec5e83fd3d70970 · report
prepare_glove_embeddings uahmad235/NER-Deep-Learning/src/model.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 48601cc3677f714b · report
allowed_transitions epwalsh/pytorch-crf/pycrf/modules/crf.py community (archive-listed) unverified MIT (permissive) · 8a5c3d6c5cdf0f7f · report
build_vocab aonotas/deep-crf/deepcrf/util.py community (archive-listed) unverified MIT (permissive) · efa5f8ef6420d58c · report
convert_examples_to_features monologg/korean-ner-pytorch/data_loader.py community (archive-listed) unverified Apache-2.0 (permissive) · 96f74869fff003c5 · report
flatten aonotas/deep-crf/deepcrf/util.py community (archive-listed) unverified MIT (permissive) · ed44eeb17583a430 · report
get_char_vocab SenticNet/aspect-extraction/model/data_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · d8fcea9be53400c5 · report
get_device epwalsh/pytorch-crf/pycrf/opts.py community (archive-listed) unverified MIT (permissive) · 2b5d5ed6870612d6 · report
get_glove_vocab SenticNet/aspect-extraction/model/data_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 150bda69614e5bc7 · report
get_labels monologg/korean-ner-pytorch/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 39747eaf4d4dd34c · report
get_logger SenticNet/aspect-extraction/model/general_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 75ed1ef1f8c3d22b · report
get_parser epwalsh/pytorch-crf/pycrf/opts.py community (archive-listed) unverified MIT (permissive) · 5d860e1e635bb337 · report
get_test_texts monologg/korean-ner-pytorch/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 1e55eeac515b209e · report
get_vocabs SenticNet/aspect-extraction/model/data_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 384baa37e7d09ae3 · report
load_vocab monologg/korean-ner-pytorch/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 7a25966763d63ede · report
load_word_matrix monologg/korean-ner-pytorch/data_loader.py community (archive-listed) unverified Apache-2.0 (permissive) · bb02eac63a26be4e · report
logsumexp epwalsh/pytorch-crf/pycrf/modules/crf.py community (archive-listed) unverified MIT (permissive) · c43b937718b773ad · report
parse_all epwalsh/pytorch-crf/pycrf/opts.py community (archive-listed) unverified MIT (permissive) · 900bd7c6020dbcd1 · report
replace_S_E_tags aonotas/deep-crf/deepcrf/evaluate.py community (archive-listed) unverified MIT (permissive) · 8a566a947be76493 · report
replace_num aonotas/deep-crf/deepcrf/util.py community (archive-listed) unverified MIT (permissive) · 7d136b2eb9ab9707 · report
uniq_tagset aonotas/deep-crf/deepcrf/evaluate.py community (archive-listed) unverified MIT (permissive) · 68a7276bb06e3bfd · report
viterbi_decode epwalsh/pytorch-crf/pycrf/modules/crf.py community (archive-listed) unverified MIT (permissive) · a76fada6d55d2d25 · report
log_sum_exp identical code first harvested elsewhere ran · honoured contract fingerprinted licence of this copy not recorded · d4329236872658c9 · report

Tasks

Feature EngineeringNamed Entity RecognitionNamed Entity Recognition (NER)POSPOS TaggingPart-Of-Speech Tagging

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Named Entity Recognition (NER) CoNLL 2003 (English) BLSTM-CNN-CRF F1 91.21 #68 of 73 Archive leaderboard report
Named Entity Recognition (NER) CoNLL++ BiLSTM-CNN-CRF F1 91.87 #10 of 11 Archive leaderboard report
Part-Of-Speech Tagging Penn Treebank BLSTM-CNN-CRF Accuracy 97.55 #11 of 20 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.

Methods

CRFLSTMSigmoid ActivationTanh Activation

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