| | --- |
| | language: |
| | - en |
| | tags: |
| | - financial NLP |
| | - named entity recognition |
| | - sequence labeling |
| | - structured extraction |
| | - hierarchical taxonomy |
| | - XBRL |
| | - iXBRL |
| | - SEC filings |
| | - financial-information-extraction |
| | datasets: |
| | - AAU-NLP/HiFi-KPI |
| | model_name: "Cal-BERT-SL1000" |
| | library_name: "transformers" |
| | pipeline_tag: "token-classification" |
| | base_model: "bert-base-uncased" |
| | task_categories: |
| | - token-classification |
| | task_ids: |
| | - named-entity-recognition |
| | - financial-information-extraction |
| | pretty_name: "Cal-BERT-SL1000: Sequence Labeling for Calculation Taxonomy KPI Extraction" |
| | size_categories: "1M<n<10M" |
| | languages: |
| | - en |
| | dataset_name: "HiFi-KPI" |
| | model_description: | |
| | Cal-BERT-SL1000 is a **BERT-based sequence labeling model** fine-tuned on the **HiFi-KPI dataset** for extracting |
| | **financial key performance indicators (KPIs)** from **SEC earnings filings (10-K & 10-Q)**. It specializes in identifying |
| | entities that are one level up the calculation taxonomy, such as revenueAbstract, earnings, and financial ratios, using **token classification**. |
| | |
| | This model is trained specifically on n=1 with the **calculation taxonomy labels** from **HiFi-KPI**, focusing on structured extraction. |
| | |
| | dataset_link: "https://huggingface.co/datasets/AAU-NLP/HiFi-KPI" |
| | repo_link: "https://github.com/rasmus393/HiFi-KPI" |
| | --- |
| | |
| | ## **Cal-BERT-SL1000** |
| |
|
| | ### **Model Description** |
| | Cal-BERT-SL1000 is a **BERT-based sequence labeling model** fine-tuned on the **[HiFi-KPI dataset](https://huggingface.co/datasets/AAU-NLP/HiFi-KPI)** for extracting **financial key performance indicators (KPIs)** from **SEC earnings filings (10-K & 10-Q)**. It specializes in identifying entities, such as revenue, earnings, etc. |
| | This model is trained on the [HiFi-KPI dataset](https://huggingface.co/datasets/AAU-NLP/HiFi-KPI) and is focused on the calculation layer taxonomy with n=1 |
| |
|
| | ### **Use Cases** |
| | - Extracting **financial KPIs** using **iXBRL calculation taxonomy** |
| | - **Financial document parsing** with entity recognition |
| |
|
| | ### **Performance** |
| | - Trained on **1,000 most frequent labels** from the **[HiFi-KPI dataset](https://huggingface.co/datasets/AAU-NLP/HiFi-KPI)** with n=1 in the calculation taxonomy |
| |
|
| | ### **Dataset & Code** |
| | - **Dataset**: [HiFi-KPI on Hugging Face](https://huggingface.co/datasets/AAU-NLP/HiFi-KPI) |
| | - **Code example**: [HiFi-KPI GitHub Repository](https://github.com/rasmus393/HiFi-KPI) |
| |
|
