--- license: mit language: - de library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - information retrieval - education - competency - course widget: [] --- # isy-thl/multilingual-e5-base-course-skill-tuned ## Overview The **isy-thl/multilingual-e5-base-course-skill-tuned** is a finetuned version of the [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) model. The primary goal of this finetuning process was to enhance the model's capabilities in information retrieval, specifically for identifying the most relevant skills associated with a given course description in the German language. ## Capabilities - **Enhanced Skill Retrieval:** - The model excels at identifying and retrieving the most relevant skills for a given course description in German, which can be leveraged for various applications in educational technology. - **Multilingual Capability:** - While optimized for German, the underlying base model [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) supports multiple languages, making it adaptable for future multilingual finetuning endeavors. - **Scalability:** - The model can handle input sequences up to 512 tokens in length, making it suitable for processing comprehensive course descriptions. ## Limitations and Considerations - **Language Limitation:** - The finetuning was specifically targeted at German language content. While the base model supports multiple languages, this particular finetuned version may not perform as well on non-German texts without additional training. - **Data Bias:** - The performance and reliability of the model are dependent on the quality of the annotated data in the training dataset. Any biases present in the training data may affect the model's output. - **Retrieval Scope:** - The model is optimized for educational contexts and may not generalize as effectively to other domains without further finetuning. ## Performance To evaluate the model, all ESCO (x=13895) and GRETA (x=23) skills were embedded using the model under assessment and stored in a vector database. For each query in the evaluation dataset, the top 30 most relevant candidates were retrieved based on cosine similarity. Metrics such as accuracy, precision, recall, NDCG, MRR, and MAP were then calculated. For reranker evaluation, the reranker was used to re-rank the top 30 candidates chosen by the fine-tuned bi-encoder model. The evaluation results were split for the ESCO and GRETA use cases: **ESCO Use Case** ![Evaluation results for ESCO use-case comparing intfloat/multilingual-e5-base, isy-thl/multilingual-e5-base-course-skill-tuned and also a version reranked with isy-thl/bge-reranker-base-course-skill-tuned](https://cdn-uploads.huggingface.co/production/uploads/64481ef1e6161a1f32e60d96/x5xqyU-_raRyVOGqGVpq-.png) **GRETA Use Case** ![Evaluation results for GRETA use-case comparing intfloat/multilingual-e5-base, isy-thl/multilingual-e5-base-course-skill-tuned and also a version reranked with isy-thl/bge-reranker-base-course-skill-tuned](https://cdn-uploads.huggingface.co/production/uploads/64481ef1e6161a1f32e60d96/DU2d1WSThMLuyvb3tNNpz.png) The results demonstrate that fine-tuning significantly enhanced the performance of the model, often more than doubling the performance of the non-fine-tuned base model. Notably, fine-tuning with training data from both use cases outperformed fine-tuning with training data from only the target skill taxonomy. This suggests that the models learn more than just specific skills from the training data and are capable of generalizing. Further research could evaluate the model's performance on an unknown skill taxonomy, where we expect it to perform better as well. The fine-tuned BI-Encoder model (isy-thl/multilingual-e5-base-course-skill-tuned) shows exceptional performance for the target task, providing significant improvements over the base model. To maximize retrieval success, it is recommended to complement the BI-Encoder model with the reranker (isy-thl/bge-reranker-base-course-skill-tuned), especially in scenarios where the computational cost is justified by the need for higher accuracy and precision. ## Usage ### Sentence Similarity ```python from sentence_transformers import SentenceTransformer import numpy as np from sklearn.metrics.pairwise import cosine_similarity # Download from the 🤗 Hub model = SentenceTransformer("isy-thl/multilingual-e5-base-course-skill-tuned") # Run inference query = [['query: ','WordPress Grundlagen\n Dieser Kurs vermittelt grundlegende Fähigkeiten zur Erstellung eines Web-Blogs in Wordpress. Sie lernen WordPress zu installieren...']] corpus = [['passage: ','WordPress'], ['passage: ','Website-Wireframe erstellen'], ['passage: ','Software für Content-Management-Systeme nutzen']] query_embeddings = model.encode(query) corpus_embeddings = model.encode(corpus) similarities = cosine_similarity(query_embeddings,corpus_embeddings) retrieved_doc_id = np.argmax(similarities) print(retrieved_doc_id) ``` ### Information Retrieval First install the langchain and chromadb library: ```bash pip install -U langchain pip install -U langchain-community pip install -U chromadb ``` Then you can load this model, create a vectordatabase and run semantic searches. ```python from langchain_community.embeddings import HuggingFaceBgeEmbeddings from langchain.vectorstores import Chroma # Download model and set embed instructions. embedding = HuggingFaceBgeEmbeddings( model_name='isy-thl/multilingual-e5-base-course-skill-tuned', query_instruction='query: '', embed_instruction='passage: ' ) # Load your documents. documents = ... # Create vector database. db = Chroma.from_documents( documents=documents, embedding=embedding, collection_metadata={'hnsw:space': 'cosine'}, ) # Search database for closest semantic matches. query = 'WordPress Grundlagen\n Dieser Kurs vermittelt grundlegende Fähigkeiten zur Erstellung eines Web-Blogs in Wordpress. Sie lernen WordPress zu installieren...' db.similarity_search_with_relevance_scores(query, 20) ``` ## Finetuning Details ### Finetuning Dataset - The model was finetuned on the [German Course Competency Alignment Dataset](pascalhuerten/course_competency_alignment_de), which includes alignments of course descriptions to the skill taxonomies of ESCO (European Skills, Competences, Qualifications and Occupations) and GRETA (a competency model for professional teaching competencies in adult education). - This dataset was compiled as part of the **WISY@KI** project, with major contributions from the **Institut für Interaktive Systeme** at the **University of Applied Sciences Lübeck**, the **Kursportal Schleswig-Holstein**, and **Weiterbildung Hessen eV**. Special thanks to colleagues from **MyEduLife** and **Trainspot**. ### Finetuning Process - **Hardware Used:** - Single NVIDIA T4 GPU with 15 GB VRAM. - **Duration:** - 2000 data points: ~15 minutes. - **Training Parameters:** ```bash torchrun --nproc_per_node 1 \ -m FlagEmbedding.baai_general_embedding.finetune.run \ --output_dir multilingual_e5_base_finetuned \ --model_name_or_path intfloat/multilingual-e5-base \ --train_data ./course_competency_alignment_de.jsonl \ --learning_rate 1e-5 \ --fp16 \ --num_train_epochs 5 \ --per_device_train_batch_size 4 \ --dataloader_drop_last True \ --normlized True \ --temperature 0.02 \ --query_max_len 512 \ --passage_max_len 64 \ --train_group_size 4 \ --negatives_cross_device \ --logging_steps 10 \ --save_steps 1500 \ --query_instruction_for_retrieval "" ``` ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base Model:** [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity - **Language:** German - **License:** MIT ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.0.1 - Transformers: 4.41.2 - PyTorch: 2.3.0+cu121 - Accelerate: 0.32.1 - Datasets: 2.20.0 - Tokenizers: 0.19.1 ### Acknowledgments Special thanks to the contributors from the **Institut für Interaktive Systeme**, **Kursportal Schleswig-Holstein**, **Weiterbildung Hessen eV**, **MyEduLife**, and **Trainspot** for their invaluable support and contributions to the dataset and finetuning process. **Funding:** This project was funded by the **Federal Ministry of Education and Research**.
BMBF Logo THL Logo WISY@KI Logo
## Model Card Authors Pascal Hürten, pascal.huerten@th-luebeck.de