KB-bert-swedish_PI-detection-general-iob

sbx/KB-bert-swedish_PI-detection-general-iob

This model was developed as part of the Mormor Karl research environment. It assesses whether each token is likely to belong to a piece of personal or sensitive information and assigns it the appropriate class (personal name, institution, geographic, transportation, age, date, other or none), distinguishing between beginnings and insides of such spans on token level.
It should be noted that this model performs best on the domain it was trained on, i.e. second-language learner essays; neither does it guarantee that all of the personal information will be detected and should only be used to assist personal information detection and classification, not completely automatize it.

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

• Developed by: Språkbanken Text, as part of the Mormor Karl research environment
• Shared by: Maria Irena Szawerna (Turtilla)
• Model type: BERT for token classification
• Language(s): Swedish
• License: GPL-3.0
• Finetuned from model: KB/bert-base-swedish-cased

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Paper: The Devil’s in the Details: the Detailedness of Classes Influences Personal Information Detection and Labeling (link)

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

This model should be used to assist annotation or de-identification efforts conducted by humans as a pre-annotation step. The detection and classification of personal information can be followed by removal or replacement of said elements.

<!-- ### Out-of-Scope Use --> <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

This model has only been trained on one domain (L2 learner essays). It does not necessarily perform well on other domains. Due to the limitations of the training data, it may also perform worse on rare or previously unseen types of personal information.
Given how high-stakes personal information detection is and that 100% accuracy cannot be guaranteed, this model should be used to assist, not automatize annotation or de-identification procedures.

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

<!-- ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> <!-- [More Information Needed] --> <!-- ### Training Procedure --> <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> <!-- #### Preprocessing [optional] --> <!-- [More Information Needed] --> <!-- #### Training Hyperparameters --> <!-- - **Training regime:** [More Information Needed] --> <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> <!-- #### Speeds, Sizes, Times [optional] --> <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> <!-- [More Information Needed] --> <!-- ## Evaluation --> <!-- This section describes the evaluation protocols and provides the results. --> <!-- ### Testing Data, Factors & Metrics --> <!-- #### Testing Data --> <!-- This should link to a Dataset Card if possible. --> <!-- [More Information Needed] --> <!-- #### Factors --> <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> <!-- [More Information Needed] --> <!-- #### Metrics --> <!-- These are the evaluation metrics being used, ideally with a description of why. --> <!-- [More Information Needed] --> <!-- ### Results --> <!-- [More Information Needed] --> <!-- #### Summary --> <!-- ## Model Examination [optional] --> <!-- Relevant interpretability work for the model goes here --> <!-- [More Information Needed] --> <!-- ## Environmental Impact --> <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> <!-- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). --> <!-- - **Hardware Type:** [More Information Needed] --> <!-- - **Hours used:** [More Information Needed] --> <!-- - **Cloud Provider:** [More Information Needed] --> <!-- - **Compute Region:** [More Information Needed] --> <!-- - **Carbon Emitted:** [More Information Needed] -->

Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

@inproceedings{szawerna-etal-2025-devils, title = "The Devil{'}s in the Details: the Detailedness of Classes Influences Personal Information Detection and Labeling", author = "Szawerna, Maria Irena and Dobnik, Simon and Mu{~n}oz S{'a}nchez, Ricardo and Volodina, Elena", editor = "Johansson, Richard and Stymne, Sara", booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)", month = mar, year = "2025", address = "Tallinn, Estonia", publisher = "University of Tartu Library", url = "https://aclanthology.org/2025.nodalida-1.70/", pages = "697--708", ISBN = "978-9908-53-109-0", abstract = "In this paper, we experiment with the effect of different levels of detailedness or granularity{---}understood as i) the number of classes, and ii) the classes' semantic depth in the sense of hypernym and hyponym relations {---} of the annotation of Personally Identifiable Information (PII) on automatic detection and labeling of such information. We fine-tune a Swedish BERT model on a corpus of Swedish learner essays annotated with a total of six PII tagsets at varying levels of granularity. We also investigate whether the presence of grammatical and lexical correction annotation in the tokens and class prevalence have an effect on predictions. We observe that the fewer total categories there are, the better the overall results are, but having a more diverse annotation facilitates fewer misclassifications for tokens containing correction annotation. We also note that the classes' internal diversity has an effect on labeling. We conclude from the results that while labeling based on the detailed annotation is difficult because of the number of classes, it is likely that models trained on such annotation rely more on the semantic content captured by contextual word embeddings rather than just the form of the tokens, making them more robust against nonstandard language." }

APA:

Maria Irena Szawerna, Simon Dobnik, Ricardo Muñoz Sánchez, and Elena Volodina. 2025. The Devil’s in the Details: the Detailedness of Classes Influences Personal Information Detection and Labeling. In Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), pages 697–708, Tallinn, Estonia. University of Tartu Library.

Model Card Authors

Maria Irena Szawerna (Turtilla)

<!-- ## Model Card Contact [More Information Needed] -->