Papers › BERT for Joint Intent Classification and Slot Filling

BERT for Joint Intent Classification and Slot Filling

28 Feb 2019arXiv:1902.10909archive 2025-07-28

Qian Chen, Zhu Zhuo, Wen Wang

Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially for rare words. Recently a new language representation model, BERT (Bidirectional Encoder Representations from Transformers), facilitates pre-training deep bidirectional representations on large-scale unlabeled corpora, and has created state-of-the-art models for a wide variety of natural language processing tasks after simple fine-tuning. However, there has not been much effort on exploring BERT for natural language understanding. In this work, we propose a joint intent classification and slot filling model based on BERT. Experimental results demonstrate that our proposed model achieves significant improvement on intent classification accuracy, slot filling F1, and sentence-level semantic frame accuracy on several public benchmark datasets, compared to the attention-based recurrent neural network models and slot-gated models.

PaperPDFCodeCode 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 32 code samples harvested from 6 repositories linked to this paper: 26 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 0 violated, 17 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 32 samples from 6 repositories, 26 ran (18 with no instrument failure; 8 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 1 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.

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

Domanjiri/joint-bert-with-tf2 mentioned on GitHubtfSyntology: not harvested report
Huawei-MRC-OSI/mrc-nlp-public mentioned on GitHubpytorchSyntology: not harvested report
MahmoudWahdan/dialog-nlu mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to On the Effect of Dropping Layers of Pre-trained Transformer Models (arXiv:2004.03844; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
Polly42Rose/SiriusIntentPredictionSlotFilling mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified report
ShawonAshraf/nlu-jointbert-dl2021 mentioned on GitHubtfSyntology: not harvested report
VinAIResearch/JointIDSF mentioned on GitHubpytorchAGPL-3.0Syntology: not harvested report
alibaba-damo-academy/spokennlp mentioned on GitHubtfApache-2.0Syntology: 11 samples, 8 ran (1 instrument-failed) · 3 unverified report
asadovsky/nn mentioned on GitHubtfSyntology: not harvested report
bhchoi/bert-for-joint-ic-sf mentioned on GitHubpytorchSyntology: not harvested report
dsindex/iclassifier mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
mangushev/intent_slot mentioned on GitHubtfMITSyntology: 5 samples, 4 ran (2 instrument-failed) · 1 unverified report
monologg/JointBERT mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 5 ran (2 instrument-failed) · 0 unverified report
sonos/svc-demographic-bias-assessment mentioned on GitHubNOASSERTIONSyntology: not harvested report
sxjscience/GluonNLP-Slot-Filling mentioned on GitHubmxnetSyntology: not harvested report
yinghao1019/Joint_learn mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
zhoucz97/JointBERT-paddle mentioned on GitHubpaddleSyntology: not harvested 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

32 samples harvested: 26 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 0 violated, 17 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
8ran · our draft was wrong
17ran
6unverified

Licence: 5 of the 32 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 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.

Polly42Rose/SiriusIntentPredictionSlotFilling community (archive-listed) 8 samples, 6 ran (0 instrument-failed) · 2 unverified
intent_accuracy quality_metrics/quality_metrics.py ran Apache-2.0 (permissive) · 0933912fab50428a · report fixture: signature labels:Tensor/1/int, preds:Tensor/2/float · returned float · level recorded 2026-09-24
load_sequences_from_file data_loading/load_data.py ran Apache-2.0 (permissive) · b2e0a020c6065fe1 · report fixture: signature path:str/0/str, voc_path:str/0/str · returned Tensor · level recorded 2026-09-24
load_words_from_file data_loading/load_data.py ran Apache-2.0 (permissive) · c807f612db31bf63 · report fixture: signature path:str/0/str, voc_path:str/0/str · returned Tensor · level recorded 2026-09-24
padding_map models/dataset.py ran fingerprinted Apache-2.0 (permissive) · 680833552e4de839 · report fixture: signature X:Tensor/2/int, padding_value:int/0/int · returned Tensor · level recorded 2026-09-24
sentence_accuracy quality_metrics/quality_metrics.py ran Apache-2.0 (permissive) · 0a3ade9a74c9987d · report fixture: signature i_labels:Tensor/1/int, i_preds:Tensor/2/float, s_labels:Tensor/2/int, s_preds:Tensor/3/float · returned float · level recorded 2026-09-24
slot_f1 quality_metrics/quality_metrics.py ran Apache-2.0 (permissive) · b62b0764cd5a1413 · report fixture: signature labels:Tensor/2/int, preds:Tensor/3/float, num_slot:int/0/int · returned tuple · level recorded 2026-09-24
load_data in 700 papers data_loading/load_data.py unverified Apache-2.0 (permissive) · 96f7ae2ec61191ba · report
preprocess_atis models/dataset.py unverified Apache-2.0 (permissive) · 89bccc2b443e9266 · report
alibaba-damo-academy/spokennlp community (archive-listed) 11 samples, 8 ran (1 instrument-failed) · 3 unverified
abridge_model_name emnlp2023-topic_segmentation/src/utils.py ran Apache-2.0 (permissive) · 0628b6fa4fa6d748 · report fixture: signature model_name_or_path:str/0/str · returned str · level recorded 2026-09-24
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
action-item-detection/script/modeling.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · d08f324f950148de · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
get_activation in 218 papers action-item-detection/script/modeling.py ran · our draft was wrong Apache-2.0 (permissive) · 5842ee67106321d6 · report fixture: signature activation_string:str/0/str · returned function · level recorded 2026-09-22
get_cn_type2video mmvts/src/evaluate.py ran Apache-2.0 (permissive) · c77e7567c42aa639 · report fixture: signature cn_type2video_file:str/0/str · returned dict · level recorded 2026-09-24
get_data_name2folder emnlp2023-topic_segmentation/src/preprocess_data.py ran Apache-2.0 (permissive) · 28f8fe33f44d2b1c · report fixture: signature config_path:str/0/str · returned SectionProxy · level recorded 2026-09-24
get_topk_preds_purely mmvts/src/evaluate.py ran Apache-2.0 (permissive) · 96d532ea3cd5bd8e · report fixture: signature labels:ndarray/1/int, probs:ndarray/1/float, topk:int/0/int · returned list · level recorded 2026-09-24
read_jsonl_file in 10 papers mmvts/src/evaluate.py ran Apache-2.0 (permissive) · 90bf04bed34edf57 · report fixture: signature in_file:str/0/str · returned list · level recorded 2026-09-24
read_total_pred_and_labels emnlp2023-topic_segmentation/src/postprocess_predictions.py ran Apache-2.0 (permissive) · e9b0cd55fca10310 · report fixture: signature data_file:str/0/str, pred_file:str/0/str · returned tuple · level recorded 2026-09-24
get_assignment_map_from_checkpoint in 32 papers action-item-detection/script/modeling.py unverified Apache-2.0 (permissive) · a8a77945aa9b653f · report
process_wiki_section_subset emnlp2023-topic_segmentation/src/preprocess_data.py unverified Apache-2.0 (permissive) · 40b50b726e7a6434 · report
tokenize_method emnlp2023-topic_segmentation/src/preprocess_data.py unverified Apache-2.0 (permissive) · e83d18c25c1278b9 · report
dsindex/iclassifier community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_soft_label evaluate.py ran · our draft was wrong no licence file found · pointer only · 46fa4973164b67e8 · report fixture: signature args:Args/0/?, pred:ndarray/1/float · returned list · level recorded 2026-09-22
mangushev/intent_slot community (archive-listed) 5 samples, 4 ran (2 instrument-failed) · 1 unverified
convert_single_example in 5 papers assistant/functions/intent_slot/preprocessor/preprocess.py ran MIT (permissive) · 047d8e25a9cd47a0 · report fixture: signature ex_index:int/0/int, example:InputExample/0/?, intent_label_list:list/1/str, slot_label_list:list/1/str, max_seq_length:int/0/int, tokenizer:SimpleTokenizer/0/? · returned IntentSlotFeatures · level recorded 2026-09-24
convert_to_unicode in 40 papers assistant/functions/intent_slot/preprocessor/tokenization.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 1923fc05163d207d · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
load_vocab in 107 papers assistant/functions/intent_slot/preprocessor/tokenization.py ran MIT (permissive) here; the stored copy is pointer only · deb4d1793cf3ba73 · report fixture: signature vocab_file:str/0/str · returned OrderedDict · level recorded 2026-09-24
printable_text in 36 papers assistant/functions/intent_slot/preprocessor/tokenization.py ran · our draft was wrong MIT (permissive) · 0e5615f8994003cf · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
file_based_input_fn_builder in 16 papers bert/run_intent_slot.py unverified MIT (permissive) · 6c079a61fb350572 · report
monologg/JointBERT community (archive-listed) 5 samples, 5 ran (2 instrument-failed) · 0 unverified
convert_examples_to_features in 134 papers data_loader.py ran Apache-2.0 (permissive) · 9d27d5015d7a3b3e · report fixture: signature examples:list/1/MockExample, max_seq_len:int/0/int, tokenizer:MockTokenizer/0/?, pad_token_label_id:int/0/int, cls_token_segment_id:int/0/int, pad_token_segment_id:int/0/int, sequence_a_segment_id:int/0/int, mask_padding_with_zero:bool/0/bool · returned list · level recorded 2026-09-24
get_args in 84 papers predict.py ran · our draft was wrong Apache-2.0 (permissive) · 107869d936646d01 · report fixture: signature pred_config:PredConfig/0/? · returned dict · level recorded 2026-09-22
get_device in 101 papers predict.py ran · our draft was wrong Apache-2.0 (permissive) · 88395eef09dea094 · report fixture: signature pred_config:PredConfig/0/? · returned str · level recorded 2026-09-22
get_intent_labels utils.py ran Apache-2.0 (permissive) · 5c324b980ac8fc2f · report fixture: signature args:Args/0/? · returned list · level recorded 2026-09-24
get_slot_labels utils.py ran Apache-2.0 (permissive) · 2756ee0a98c809b9 · report fixture: signature args:Args/0/? · returned list · level recorded 2026-09-24
yinghao1019/Joint_learn community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
read_file in 112 papers predict.py ran · our draft was wrong no licence file found · pointer only · 7b9905a68c0add30 · report fixture: signature pred_config:PredConfig/0/? · returned list · level recorded 2026-09-22
set_device in 16 papers predict.py ran · our draft was wrong no licence file found · pointer only · cfd666d38b923d90 · report fixture: signature pred_config:PredConfig/0/? · returned device · level recorded 2026-09-22

Tasks

General ClassificationIntent ClassificationIntent DetectionNatural Language UnderstandingSentenceSlot Fillingintent-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Intent Detection ATIS Joint BERT + CRF Accuracy 97.9 #6 of 16 Archive leaderboard report
Intent Detection ATIS Joint BERT Accuracy 97.5 #10 of 16 Archive leaderboard report
Slot Filling ATIS Joint BERT F1 0.961 #3 of 14 Archive leaderboard report
Slot Filling ATIS Joint BERT + CRF F1 0.96 #6 of 14 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

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